{"step": 100, "train_l1": 0.13146860897541046, "kl": 0.10187894105911255, "validation_action_l1": 0.09280722588300705, "validation_l1_per_dimension": [0.07816407084465027, 0.10187091678380966, 0.23058712482452393, 0.0444936528801918, 0.030699659138917923, 0.05433621257543564, 0.10949895530939102], "elapsed_s": 41.316221475601196} {"step": 200, "train_l1": 0.10305464267730713, "kl": 0.03586076200008392, "validation_action_l1": 0.067633256316185, "validation_l1_per_dimension": [0.04720250144600868, 0.05945651978254318, 0.19678711891174316, 0.021004339680075645, 0.03865695372223854, 0.021993841975927353, 0.08833148330450058], "elapsed_s": 80.11179614067078} {"step": 300, "train_l1": 0.08127797394990921, "kl": 0.017203528434038162, "validation_action_l1": 0.06552847474813461, "validation_l1_per_dimension": [0.050799187272787094, 0.07564572989940643, 0.1715668886899948, 0.017337635159492493, 0.02601581998169422, 0.015308817848563194, 0.10202521830797195], "elapsed_s": 117.71846580505371} {"step": 400, "train_l1": 0.0716642439365387, "kl": 0.011325132101774216, "validation_action_l1": 0.05363447219133377, "validation_l1_per_dimension": [0.05846063420176506, 0.06229221820831299, 0.14470861852169037, 0.01751367375254631, 0.022104976698756218, 0.01713728718459606, 0.05322389677166939], "elapsed_s": 155.6074640750885} {"step": 500, "train_l1": 0.06432721763849258, "kl": 0.00902109406888485, "validation_action_l1": 0.05229271203279495, "validation_l1_per_dimension": [0.03798650950193405, 0.03487427160143852, 0.1928090900182724, 0.014436599798500538, 0.01787411794066429, 0.011733346618711948, 0.05633505806326866], "elapsed_s": 192.20194625854492} {"step": 600, "train_l1": 0.05620095878839493, "kl": 0.007853465154767036, "validation_action_l1": 0.059100985527038574, "validation_l1_per_dimension": [0.053985241800546646, 0.03205488622188568, 0.20284873247146606, 0.011084877885878086, 0.014247095212340355, 0.008130587637424469, 0.09135547280311584], "elapsed_s": 229.63873529434204} {"step": 700, "train_l1": 0.052930235862731934, "kl": 0.006222969852387905, "validation_action_l1": 0.046723686158657074, "validation_l1_per_dimension": [0.03440950810909271, 0.05019500106573105, 0.16682776808738708, 0.011017600074410439, 0.015187053941190243, 0.007983513176441193, 0.041445352137088776], "elapsed_s": 265.27122616767883} {"step": 800, "train_l1": 0.04625214636325836, "kl": 0.006482606288045645, "validation_action_l1": 0.041640929877758026, "validation_l1_per_dimension": [0.03530406206846237, 0.024224789813160896, 0.14733898639678955, 0.008042619563639164, 0.01168654952198267, 0.008142339065670967, 0.05674714967608452], "elapsed_s": 302.61764430999756} {"step": 900, "train_l1": 0.045957352966070175, "kl": 0.0048690796829760075, "validation_action_l1": 0.04201969504356384, "validation_l1_per_dimension": [0.03994467481970787, 0.03283413499593735, 0.11170049756765366, 0.008446499705314636, 0.011966804042458534, 0.008155365474522114, 0.08108988404273987], "elapsed_s": 340.1698877811432} {"step": 1000, "train_l1": 0.03962818905711174, "kl": 0.006122647784650326, "validation_action_l1": 0.03738505020737648, "validation_l1_per_dimension": [0.03730127960443497, 0.038458872586488724, 0.12619929015636444, 0.0073593915440142155, 0.011399440467357635, 0.005676575005054474, 0.03530050441622734], "elapsed_s": 377.42086029052734} {"step": 1100, "train_l1": 0.041377823799848557, "kl": 0.0034091901034116745, "validation_action_l1": 0.039771031588315964, "validation_l1_per_dimension": [0.05662715062499046, 0.03745577484369278, 0.13168340921401978, 0.007123469840735197, 0.01121489703655243, 0.0050496007315814495, 0.029242929071187973], "elapsed_s": 413.49367094039917} {"step": 1200, "train_l1": 0.04011264815926552, "kl": 0.004775689449161291, "validation_action_l1": 0.03929446265101433, "validation_l1_per_dimension": [0.034384388476610184, 0.0351891852915287, 0.12242263555526733, 0.007543314713984728, 0.015637921169400215, 0.006059485953301191, 0.0538242943584919], "elapsed_s": 451.1854078769684} {"step": 1300, "train_l1": 0.03452405706048012, "kl": 0.004483358468860388, "validation_action_l1": 0.04111308604478836, "validation_l1_per_dimension": [0.042582109570503235, 0.033694587647914886, 0.11012429744005203, 0.007612996269017458, 0.009093211032450199, 0.005408757366240025, 0.07927564531564713], "elapsed_s": 487.7076096534729} {"step": 1400, "train_l1": 0.038548219949007034, "kl": 0.0043453858233988285, "validation_action_l1": 0.033799320459365845, "validation_l1_per_dimension": [0.03156118839979172, 0.03334542363882065, 0.12006104737520218, 0.006090251263231039, 0.010252203792333603, 0.005598420277237892, 0.029686711728572845], "elapsed_s": 527.35515666008} {"step": 1500, "train_l1": 0.036970026791095734, "kl": 0.00243378896266222, "validation_action_l1": 0.03553103655576706, "validation_l1_per_dimension": [0.03563147410750389, 0.03525358438491821, 0.11884842813014984, 0.007515653036534786, 0.010538808070123196, 0.004699996672570705, 0.036229297518730164], "elapsed_s": 559.234902381897} {"step": 1600, "train_l1": 0.03770630061626434, "kl": 0.0035678958520293236, "validation_action_l1": 0.03589622303843498, "validation_l1_per_dimension": [0.05351061001420021, 0.046067897230386734, 0.09384488314390182, 0.0067635816521942616, 0.010131930001080036, 0.0056890142150223255, 0.03526564687490463], "elapsed_s": 582.2651200294495} {"step": 1700, "train_l1": 0.03212211653590202, "kl": 0.004199719522148371, "validation_action_l1": 0.031133512035012245, "validation_l1_per_dimension": [0.026234807446599007, 0.03362104296684265, 0.11235807090997696, 0.006667998619377613, 0.010790862143039703, 0.005779580678790808, 0.02248223125934601], "elapsed_s": 601.2652688026428} {"step": 1800, "train_l1": 0.03278101608157158, "kl": 0.004778306465595961, "validation_action_l1": 0.03313739597797394, "validation_l1_per_dimension": [0.0358760766685009, 0.02084006927907467, 0.0970512107014656, 0.006476110313087702, 0.008776930160820484, 0.00352459866553545, 0.0594167597591877], "elapsed_s": 619.0339758396149} {"step": 1900, "train_l1": 0.026625435799360275, "kl": 0.004660040605813265, "validation_action_l1": 0.036702871322631836, "validation_l1_per_dimension": [0.04368339851498604, 0.04503660649061203, 0.11234349012374878, 0.005954611115157604, 0.008298724889755249, 0.0041794320568442345, 0.03742383420467377], "elapsed_s": 628.3762390613556} {"step": 2000, "train_l1": 0.032203443348407745, "kl": 0.003317706286907196, "validation_action_l1": 0.028840474784374237, "validation_l1_per_dimension": [0.022702766582369804, 0.03716280683875084, 0.09792443364858627, 0.0061716861091554165, 0.00920456275343895, 0.004265194293111563, 0.024451885372400284], "elapsed_s": 633.6278524398804} {"step": 2100, "train_l1": 0.025636998936533928, "kl": 0.0034121591597795486, "validation_action_l1": 0.02481253817677498, "validation_l1_per_dimension": [0.023256951943039894, 0.021068155765533447, 0.08810212463140488, 0.004711694084107876, 0.007239696104079485, 0.0031690322794020176, 0.026140112429857254], "elapsed_s": 639.3118839263916} {"step": 2200, "train_l1": 0.024929091334342957, "kl": 0.0033565405756235123, "validation_action_l1": 0.03474395349621773, "validation_l1_per_dimension": [0.040356528013944626, 0.042595237493515015, 0.11428830772638321, 0.004989237058907747, 0.007508931681513786, 0.0035118989180773497, 0.029957536607980728], "elapsed_s": 644.5831406116486} {"step": 2300, "train_l1": 0.025508439168334007, "kl": 0.0034825168550014496, "validation_action_l1": 0.03813648223876953, "validation_l1_per_dimension": [0.041753705590963364, 0.029600057750940323, 0.12252155691385269, 0.005415027029812336, 0.008128712885081768, 0.0042811003513634205, 0.05525524541735649], "elapsed_s": 649.8210275173187} {"step": 2400, "train_l1": 0.02940937876701355, "kl": 0.003496288787573576, "validation_action_l1": 0.03425174206495285, "validation_l1_per_dimension": [0.02603248693048954, 0.04195919260382652, 0.11621023714542389, 0.005708946380764246, 0.009719936177134514, 0.003393558319658041, 0.0367378406226635], "elapsed_s": 655.0920505523682} {"step": 2500, "train_l1": 0.0270503181964159, "kl": 0.0021730498410761356, "validation_action_l1": 0.023223496973514557, "validation_l1_per_dimension": [0.021980086341500282, 0.0220448337495327, 0.08459088951349258, 0.0049158427864313126, 0.007212247233837843, 0.003226054599508643, 0.018594520166516304], "elapsed_s": 660.4096295833588} {"step": 2600, "train_l1": 0.0256988313049078, "kl": 0.001995130442082882, "validation_action_l1": 0.031068645417690277, "validation_l1_per_dimension": [0.026462242007255554, 0.032943300902843475, 0.10580415278673172, 0.0058090342208743095, 0.010311858728528023, 0.0030701716896146536, 0.033079780638217926], "elapsed_s": 665.7228486537933} {"step": 2700, "train_l1": 0.02190260961651802, "kl": 0.0037978566251695156, "validation_action_l1": 0.025835104286670685, "validation_l1_per_dimension": [0.033389635384082794, 0.03589799627661705, 0.0751679316163063, 0.005529141519218683, 0.005805246066302061, 0.0033044975716620684, 0.021751293912529945], "elapsed_s": 670.9847249984741} {"step": 2800, "train_l1": 0.025376543402671814, "kl": 0.0036820066161453724, "validation_action_l1": 0.029075726866722107, "validation_l1_per_dimension": [0.04055197536945343, 0.039644017815589905, 0.0824965238571167, 0.005153427366167307, 0.008853331208229065, 0.0030480679124593735, 0.02378273941576481], "elapsed_s": 676.3341679573059} {"step": 2900, "train_l1": 0.02407577633857727, "kl": 0.0036001685075461864, "validation_action_l1": 0.02768072858452797, "validation_l1_per_dimension": [0.030707109719514847, 0.038503218442201614, 0.0801510363817215, 0.005546835716813803, 0.007163078989833593, 0.003224174492061138, 0.028469640761613846], "elapsed_s": 681.7762866020203} {"step": 3000, "train_l1": 0.021422792226076126, "kl": 0.0016684643924236298, "validation_action_l1": 0.04180442541837692, "validation_l1_per_dimension": [0.04328830540180206, 0.057840850204229355, 0.10392400622367859, 0.006109457463026047, 0.008822595700621605, 0.0031157906632870436, 0.06952997297048569], "elapsed_s": 687.0881276130676} {"step": 3100, "train_l1": 0.023470716550946236, "kl": 0.003537811804562807, "validation_action_l1": 0.032827287912368774, "validation_l1_per_dimension": [0.04052041098475456, 0.045041631907224655, 0.10701263695955276, 0.005692769773304462, 0.009453332982957363, 0.0027951786760240793, 0.01927506923675537], "elapsed_s": 692.5892353057861} {"step": 3200, "train_l1": 0.02215721271932125, "kl": 0.003181502688676119, "validation_action_l1": 0.02933899313211441, "validation_l1_per_dimension": [0.03407568484544754, 0.041186075657606125, 0.08287416398525238, 0.005445606075227261, 0.008463588543236256, 0.0027921919245272875, 0.030535640195012093], "elapsed_s": 697.8927941322327} {"step": 3300, "train_l1": 0.022784272208809853, "kl": 0.0038951467722654343, "validation_action_l1": 0.02738051675260067, "validation_l1_per_dimension": [0.032083578407764435, 0.0282583124935627, 0.09740033000707626, 0.004549089353531599, 0.008724823594093323, 0.002643645042553544, 0.018003830686211586], "elapsed_s": 703.2349152565002} {"step": 3400, "train_l1": 0.021186744794249535, "kl": 0.0036247028037905693, "validation_action_l1": 0.030004465952515602, "validation_l1_per_dimension": [0.029778555035591125, 0.03522249311208725, 0.09978915750980377, 0.005297690164297819, 0.008738348260521889, 0.0028081871569156647, 0.028396816924214363], "elapsed_s": 708.4831688404083} {"step": 3500, "train_l1": 0.021023515611886978, "kl": 0.0017866743728518486, "validation_action_l1": 0.03181641921401024, "validation_l1_per_dimension": [0.03919774666428566, 0.034669212996959686, 0.09656385332345963, 0.006042224820703268, 0.010107075795531273, 0.0027442125137895346, 0.033390600234270096], "elapsed_s": 713.927969455719} {"step": 3600, "train_l1": 0.020006803795695305, "kl": 0.003170579671859741, "validation_action_l1": 0.03025876171886921, "validation_l1_per_dimension": [0.03802453354001045, 0.03357437998056412, 0.07455894351005554, 0.004998629912734032, 0.009006239473819733, 0.002707642735913396, 0.04894094169139862], "elapsed_s": 719.237058877945} {"step": 3700, "train_l1": 0.020283732563257217, "kl": 0.0018096496351063251, "validation_action_l1": 0.024788854643702507, "validation_l1_per_dimension": [0.02713833376765251, 0.019405657425522804, 0.08474701642990112, 0.004516856744885445, 0.008529686369001865, 0.0027223622892051935, 0.026462065055966377], "elapsed_s": 724.5790770053864} {"step": 3800, "train_l1": 0.018861429765820503, "kl": 0.002186109311878681, "validation_action_l1": 0.024405989795923233, "validation_l1_per_dimension": [0.023891424760222435, 0.03251662850379944, 0.07862923294305801, 0.004579029977321625, 0.007084045093506575, 0.0023947805166244507, 0.021746791899204254], "elapsed_s": 729.9171674251556} {"step": 3900, "train_l1": 0.017041096463799477, "kl": 0.0018712906166911125, "validation_action_l1": 0.02307015471160412, "validation_l1_per_dimension": [0.02076532319188118, 0.014154328033328056, 0.09361018985509872, 0.0048043797723948956, 0.008224555291235447, 0.00255004339851439, 0.01738225482404232], "elapsed_s": 735.2260854244232} {"step": 4000, "train_l1": 0.016357894986867905, "kl": 0.0027264743112027645, "validation_action_l1": 0.026373565196990967, "validation_l1_per_dimension": [0.03894810378551483, 0.03721616044640541, 0.07523025572299957, 0.0038513641338795424, 0.007259289268404245, 0.002737523289397359, 0.019372256472706795], "elapsed_s": 740.5416197776794} {"step": 4100, "train_l1": 0.018453450873494148, "kl": 0.005082595627754927, "validation_action_l1": 0.023261351510882378, "validation_l1_per_dimension": [0.030260244384407997, 0.030485162511467934, 0.06411837786436081, 0.0036662970669567585, 0.005494040437042713, 0.0027068268973380327, 0.02609851397573948], "elapsed_s": 746.1190176010132} {"step": 4200, "train_l1": 0.01886192336678505, "kl": 0.0029783756472170353, "validation_action_l1": 0.026215653866529465, "validation_l1_per_dimension": [0.028726695105433464, 0.03251015394926071, 0.08052405714988708, 0.004043842200189829, 0.00814146175980568, 0.002413082867860794, 0.027150284498929977], "elapsed_s": 751.4133150577545} {"step": 4300, "train_l1": 0.01956707052886486, "kl": 0.0039039328694343567, "validation_action_l1": 0.021076731383800507, "validation_l1_per_dimension": [0.025509675964713097, 0.02399066463112831, 0.06307878345251083, 0.004482528194785118, 0.006513779517263174, 0.002455933252349496, 0.021505750715732574], "elapsed_s": 756.7132799625397} {"step": 4400, "train_l1": 0.01930258795619011, "kl": 0.00438168179243803, "validation_action_l1": 0.031232193112373352, "validation_l1_per_dimension": [0.034601613879203796, 0.031035928055644035, 0.09151435643434525, 0.005441367160528898, 0.009607183746993542, 0.002422909252345562, 0.044001996517181396], "elapsed_s": 762.0946741104126} {"step": 4500, "train_l1": 0.01633976586163044, "kl": 0.0044320449233055115, "validation_action_l1": 0.023271648213267326, "validation_l1_per_dimension": [0.024296311661601067, 0.021763181313872337, 0.055676352232694626, 0.0038359800819307566, 0.006773211527615786, 0.0025945778470486403, 0.04796192795038223], "elapsed_s": 767.4854764938354} {"step": 4600, "train_l1": 0.02570953406393528, "kl": 0.003185790032148361, "validation_action_l1": 0.029471158981323242, "validation_l1_per_dimension": [0.02617586776614189, 0.029324151575565338, 0.10016266256570816, 0.005283041391521692, 0.009437106549739838, 0.0022403199691325426, 0.03367495536804199], "elapsed_s": 772.6724362373352} {"step": 4700, "train_l1": 0.01563371904194355, "kl": 0.004298460204154253, "validation_action_l1": 0.029341664165258408, "validation_l1_per_dimension": [0.03640890493988991, 0.027548423036932945, 0.08101437985897064, 0.0031987593974918127, 0.005744673311710358, 0.002792160492390394, 0.048684343695640564], "elapsed_s": 777.985493183136} {"step": 4800, "train_l1": 0.017808834090828896, "kl": 0.00494799530133605, "validation_action_l1": 0.02260628715157509, "validation_l1_per_dimension": [0.03590869903564453, 0.02527071163058281, 0.06627506762742996, 0.0035342874471098185, 0.00569695420563221, 0.0021454242523759604, 0.01941286027431488], "elapsed_s": 783.2899510860443} {"step": 4900, "train_l1": 0.017775550484657288, "kl": 0.0038732225075364113, "validation_action_l1": 0.02156471274793148, "validation_l1_per_dimension": [0.023079238831996918, 0.032534919679164886, 0.06251441687345505, 0.004576430656015873, 0.006167179439216852, 0.0026310551911592484, 0.019449740648269653], "elapsed_s": 788.6808459758759} {"step": 5000, "train_l1": 0.013725466094911098, "kl": 0.00464326748624444, "validation_action_l1": 0.02347980998456478, "validation_l1_per_dimension": [0.0202624574303627, 0.01344465371221304, 0.08544428646564484, 0.004175323527306318, 0.008160821162164211, 0.0020146428141742945, 0.030856488272547722], "elapsed_s": 794.0027215480804} {"step": 5100, "train_l1": 0.022539611905813217, "kl": 0.004203857388347387, "validation_action_l1": 0.029961107298731804, "validation_l1_per_dimension": [0.058035142719745636, 0.03640526533126831, 0.07423469424247742, 0.004467475228011608, 0.008199237287044525, 0.002504956442862749, 0.025880973786115646], "elapsed_s": 799.6407866477966} {"step": 5200, "train_l1": 0.015328378416597843, "kl": 0.003224029205739498, "validation_action_l1": 0.02679765410721302, "validation_l1_per_dimension": [0.03617217019200325, 0.03756142035126686, 0.08281679451465607, 0.004680844955146313, 0.007823492400348186, 0.0023496723733842373, 0.016179200261831284], "elapsed_s": 804.9501550197601} {"step": 5300, "train_l1": 0.01544218696653843, "kl": 0.002994806971400976, "validation_action_l1": 0.020847246050834656, "validation_l1_per_dimension": [0.026829546317458153, 0.020716136321425438, 0.07405242323875427, 0.003638042602688074, 0.006937148980796337, 0.0024330720771104097, 0.011324360966682434], "elapsed_s": 810.1975784301758} {"step": 5400, "train_l1": 0.014813985675573349, "kl": 0.005032526794821024, "validation_action_l1": 0.02333023026585579, "validation_l1_per_dimension": [0.021409111097455025, 0.023668503388762474, 0.09200824052095413, 0.0038304633926600218, 0.0068188984878361225, 0.002024370711296797, 0.013552017509937286], "elapsed_s": 815.6077919006348} {"step": 5500, "train_l1": 0.014310299418866634, "kl": 0.004796185065060854, "validation_action_l1": 0.024584295228123665, "validation_l1_per_dimension": [0.015815049409866333, 0.018050428479909897, 0.0769449844956398, 0.0041438015177845955, 0.00727900629863143, 0.0022784732282161713, 0.047578319907188416], "elapsed_s": 820.8406429290771} {"step": 5600, "train_l1": 0.016720470041036606, "kl": 0.004396857228130102, "validation_action_l1": 0.030197447165846825, "validation_l1_per_dimension": [0.04066991060972214, 0.038550861179828644, 0.08629874140024185, 0.004210404120385647, 0.007854082621634007, 0.002319970168173313, 0.031478166580200195], "elapsed_s": 826.195826292038} {"step": 5700, "train_l1": 0.0143436836078763, "kl": 0.004162820056080818, "validation_action_l1": 0.021345805376768112, "validation_l1_per_dimension": [0.03388324752449989, 0.024349600076675415, 0.06316258758306503, 0.003352540312334895, 0.00489749014377594, 0.0020662921015173197, 0.01770888641476631], "elapsed_s": 831.4988491535187} {"step": 5800, "train_l1": 0.014384862035512924, "kl": 0.005196298938244581, "validation_action_l1": 0.031322088092565536, "validation_l1_per_dimension": [0.03845992311835289, 0.042892053723335266, 0.10958345234394073, 0.004539355635643005, 0.008635989390313625, 0.0017733554122969508, 0.01337046641856432], "elapsed_s": 836.8260567188263} {"step": 5900, "train_l1": 0.016259318217635155, "kl": 0.003877912648022175, "validation_action_l1": 0.02981969527900219, "validation_l1_per_dimension": [0.03110363334417343, 0.03252829983830452, 0.10009276866912842, 0.0046349479816854, 0.008856483735144138, 0.0019637763034552336, 0.029557975009083748], "elapsed_s": 841.9857180118561} {"step": 6000, "train_l1": 0.014240996912121773, "kl": 0.006348594557493925, "validation_action_l1": 0.0194289181381464, "validation_l1_per_dimension": [0.017508490011096, 0.019939659163355827, 0.06092976778745651, 0.003671112237498164, 0.0059855845756828785, 0.0018443622393533587, 0.026123439893126488], "elapsed_s": 847.1941497325897} {"step": 6100, "train_l1": 0.013521517626941204, "kl": 0.005874708294868469, "validation_action_l1": 0.016272474080324173, "validation_l1_per_dimension": [0.018995683640241623, 0.018924525007605553, 0.05298037827014923, 0.003803991014137864, 0.005608520936220884, 0.001644172822125256, 0.011950051411986351], "elapsed_s": 852.9661202430725} {"step": 6200, "train_l1": 0.014394783414900303, "kl": 0.00524826580658555, "validation_action_l1": 0.024281714111566544, "validation_l1_per_dimension": [0.031841352581977844, 0.021957246586680412, 0.06825757026672363, 0.0033334994222968817, 0.0054337028414011, 0.0017748101381585002, 0.03737381100654602], "elapsed_s": 858.2431771755219} {"step": 6300, "train_l1": 0.015086180530488491, "kl": 0.003888300620019436, "validation_action_l1": 0.02546139992773533, "validation_l1_per_dimension": [0.027144791558384895, 0.03994476795196533, 0.08300589770078659, 0.003720341483131051, 0.007467138580977917, 0.0021530345547944307, 0.014793829061090946], "elapsed_s": 863.5758635997772} {"step": 6400, "train_l1": 0.015556054189801216, "kl": 0.00673519354313612, "validation_action_l1": 0.018174078315496445, "validation_l1_per_dimension": [0.017379572615027428, 0.013329541310667992, 0.06106079742312431, 0.003631681203842163, 0.0067301224917173386, 0.0016410137759521604, 0.023445826023817062], "elapsed_s": 868.9521973133087} {"step": 6500, "train_l1": 0.016205839812755585, "kl": 0.0041203685104846954, "validation_action_l1": 0.021522726863622665, "validation_l1_per_dimension": [0.01579812355339527, 0.02147379331290722, 0.06962811946868896, 0.004008687566965818, 0.007619108073413372, 0.0017756822053343058, 0.030355578288435936], "elapsed_s": 874.2466068267822} {"step": 6600, "train_l1": 0.013914638198912144, "kl": 0.004358038771897554, "validation_action_l1": 0.03248806297779083, "validation_l1_per_dimension": [0.03553440794348717, 0.0337853878736496, 0.08991353213787079, 0.004477727226912975, 0.009388106875121593, 0.0020670732483267784, 0.052250202745199203], "elapsed_s": 879.5436387062073} {"step": 6700, "train_l1": 0.014543269760906696, "kl": 0.005813508294522762, "validation_action_l1": 0.02565053477883339, "validation_l1_per_dimension": [0.02312018722295761, 0.030431021004915237, 0.09629733115434647, 0.004935513716191053, 0.009810075163841248, 0.0017698319861665368, 0.01318978052586317], "elapsed_s": 885.1426632404327} {"step": 6800, "train_l1": 0.013007694855332375, "kl": 0.002956264652311802, "validation_action_l1": 0.027789335697889328, "validation_l1_per_dimension": [0.02862461842596531, 0.027853792533278465, 0.0849369689822197, 0.003820161335170269, 0.00784567091614008, 0.0020130565389990807, 0.03943107649683952], "elapsed_s": 894.2001588344574} {"step": 6900, "train_l1": 0.01266026496887207, "kl": 0.006975000724196434, "validation_action_l1": 0.03376699239015579, "validation_l1_per_dimension": [0.05135978385806084, 0.046046216040849686, 0.10496095567941666, 0.0036639231257140636, 0.007387756370007992, 0.0017189756035804749, 0.021231353282928467], "elapsed_s": 919.164941072464} {"step": 7000, "train_l1": 0.012184380553662777, "kl": 0.005781346932053566, "validation_action_l1": 0.024719970300793648, "validation_l1_per_dimension": [0.031216805800795555, 0.036561571061611176, 0.08327310532331467, 0.003634140593931079, 0.007043174933642149, 0.0019330235663801432, 0.009377953596413136], "elapsed_s": 942.2868540287018} {"step": 7100, "train_l1": 0.013661961071193218, "kl": 0.0052564144134521484, "validation_action_l1": 0.024516427889466286, "validation_l1_per_dimension": [0.03548351302742958, 0.02160503715276718, 0.078903429210186, 0.0033535039983689785, 0.006416096817702055, 0.0017027892172336578, 0.024150626733899117], "elapsed_s": 962.036634683609} {"step": 7200, "train_l1": 0.014902148395776749, "kl": 0.00506053538993001, "validation_action_l1": 0.024644922465085983, "validation_l1_per_dimension": [0.02950439788401127, 0.030102528631687164, 0.060353782027959824, 0.00268257106654346, 0.004582831636071205, 0.0018405822338536382, 0.043447770178318024], "elapsed_s": 981.5120379924774} {"step": 7300, "train_l1": 0.0130741186439991, "kl": 0.004616974852979183, "validation_action_l1": 0.02517702989280224, "validation_l1_per_dimension": [0.02629704400897026, 0.031095294281840324, 0.084185391664505, 0.0034230125602334738, 0.006659924518316984, 0.001496496144682169, 0.023082053288817406], "elapsed_s": 1003.8924479484558} {"step": 7400, "train_l1": 0.012069257907569408, "kl": 0.00755825312808156, "validation_action_l1": 0.022826623171567917, "validation_l1_per_dimension": [0.032468754798173904, 0.02767890691757202, 0.06321962922811508, 0.003065973985940218, 0.005926451180130243, 0.001773057272657752, 0.025653598830103874], "elapsed_s": 1022.8250885009766} {"step": 7500, "train_l1": 0.014001412317156792, "kl": 0.008272705599665642, "validation_action_l1": 0.03161740303039551, "validation_l1_per_dimension": [0.042572252452373505, 0.03848612308502197, 0.07444994151592255, 0.003852743888273835, 0.007377804722636938, 0.00180135911796242, 0.0527816079556942], "elapsed_s": 1028.0797843933105} {"step": 7600, "train_l1": 0.015052261762320995, "kl": 0.004489704500883818, "validation_action_l1": 0.03662939742207527, "validation_l1_per_dimension": [0.03816264495253563, 0.030498767271637917, 0.09756026417016983, 0.005116729531437159, 0.009612519294023514, 0.0018880654824897647, 0.07356678694486618], "elapsed_s": 1032.9873979091644} {"step": 7700, "train_l1": 0.012894771993160248, "kl": 0.006739578675478697, "validation_action_l1": 0.02576354518532753, "validation_l1_per_dimension": [0.025236647576093674, 0.026848502457141876, 0.09633512049913406, 0.004236696753650904, 0.00820217840373516, 0.0017325322842225432, 0.017753150314092636], "elapsed_s": 1038.4188146591187} {"step": 7800, "train_l1": 0.014758962206542492, "kl": 0.006145246792584658, "validation_action_l1": 0.027270542457699776, "validation_l1_per_dimension": [0.03568686172366142, 0.02090378850698471, 0.08048701286315918, 0.0036134824622422457, 0.006603760179132223, 0.0017777641769498587, 0.041821129620075226], "elapsed_s": 1043.9842681884766} {"step": 7900, "train_l1": 0.012783871032297611, "kl": 0.006762789096683264, "validation_action_l1": 0.018060334026813507, "validation_l1_per_dimension": [0.02602909877896309, 0.025587085634469986, 0.04532219469547272, 0.0025665040593594313, 0.003829031018540263, 0.001650931197218597, 0.02143748663365841], "elapsed_s": 1049.3760435581207} {"step": 8000, "train_l1": 0.012664428912103176, "kl": 0.006895984057337046, "validation_action_l1": 0.03571855276823044, "validation_l1_per_dimension": [0.04527867212891579, 0.039438359439373016, 0.10257430374622345, 0.0038755398709326982, 0.00797587912529707, 0.0017237340798601508, 0.04916336387395859], "elapsed_s": 1054.5877559185028} {"step": 8100, "train_l1": 0.010940355248749256, "kl": 0.005684543401002884, "validation_action_l1": 0.022235354408621788, "validation_l1_per_dimension": [0.024482442066073418, 0.030289271846413612, 0.06890459358692169, 0.0035813094582408667, 0.007101400755345821, 0.0016030003316700459, 0.019685465842485428], "elapsed_s": 1060.1913356781006} {"step": 8200, "train_l1": 0.016391877084970474, "kl": 0.007403769064694643, "validation_action_l1": 0.02812913805246353, "validation_l1_per_dimension": [0.04114961251616478, 0.03579629585146904, 0.08448106795549393, 0.004870266187936068, 0.008943727239966393, 0.002050073118880391, 0.019612930715084076], "elapsed_s": 1065.461317062378} {"step": 8300, "train_l1": 0.013889736495912075, "kl": 0.008935948833823204, "validation_action_l1": 0.021778957918286324, "validation_l1_per_dimension": [0.02774232253432274, 0.03017250820994377, 0.06045869365334511, 0.0034757673274725676, 0.0064850663766264915, 0.00175963481888175, 0.022358708083629608], "elapsed_s": 1070.7352411746979} {"step": 8400, "train_l1": 0.010630966164171696, "kl": 0.004537087865173817, "validation_action_l1": 0.016398239880800247, "validation_l1_per_dimension": [0.022826574742794037, 0.018479343503713608, 0.04872942343354225, 0.003116677515208721, 0.005995664745569229, 0.001552740577608347, 0.014087256975471973], "elapsed_s": 1075.980853319168} {"step": 8500, "train_l1": 0.010809225961565971, "kl": 0.006476517766714096, "validation_action_l1": 0.02458028495311737, "validation_l1_per_dimension": [0.029754653573036194, 0.02476150169968605, 0.08012575656175613, 0.0032003414817154408, 0.006076461169868708, 0.0015511240344494581, 0.026592155918478966], "elapsed_s": 1081.2907519340515} {"step": 8600, "train_l1": 0.010914060287177563, "kl": 0.0077050128020346165, "validation_action_l1": 0.027021151036024094, "validation_l1_per_dimension": [0.03012433834373951, 0.033014360815286636, 0.08470513671636581, 0.00326643418520689, 0.0066743092611432076, 0.0014342523645609617, 0.029929231852293015], "elapsed_s": 1086.6032106876373} {"step": 8700, "train_l1": 0.011468283832073212, "kl": 0.007449106313288212, "validation_action_l1": 0.022366929799318314, "validation_l1_per_dimension": [0.025167779996991158, 0.03229919448494911, 0.07647693157196045, 0.003092982806265354, 0.005572095513343811, 0.00160276482347399, 0.012356751598417759], "elapsed_s": 1091.9472992420197} {"step": 8800, "train_l1": 0.011064288206398487, "kl": 0.007469879928976297, "validation_action_l1": 0.02764071337878704, "validation_l1_per_dimension": [0.033173009753227234, 0.03046620450913906, 0.08358331024646759, 0.0035597123205661774, 0.006380940321832895, 0.001761924708262086, 0.034559886902570724], "elapsed_s": 1097.1554169654846} {"step": 8900, "train_l1": 0.011292978189885616, "kl": 0.01074613630771637, "validation_action_l1": 0.024854116141796112, "validation_l1_per_dimension": [0.03303508087992668, 0.04277888312935829, 0.07254856079816818, 0.002916166326031089, 0.005362312309443951, 0.0017871891614049673, 0.015550627373158932], "elapsed_s": 1102.401790380478} {"step": 9000, "train_l1": 0.013046070002019405, "kl": 0.008373898454010487, "validation_action_l1": 0.025627177208662033, "validation_l1_per_dimension": [0.02442987635731697, 0.022459933534264565, 0.080962173640728, 0.0036839679814875126, 0.0074249557219445705, 0.0019871077965945005, 0.0384422205388546], "elapsed_s": 1107.6900596618652} {"step": 9100, "train_l1": 0.01318962499499321, "kl": 0.007624455727636814, "validation_action_l1": 0.026439812034368515, "validation_l1_per_dimension": [0.037067823112010956, 0.04230302572250366, 0.07676272839307785, 0.0043145595118403435, 0.008281677030026913, 0.0014578532427549362, 0.014891018159687519], "elapsed_s": 1113.276798248291} {"step": 9200, "train_l1": 0.011889796704053879, "kl": 0.009914874099195004, "validation_action_l1": 0.027908701449632645, "validation_l1_per_dimension": [0.03603340685367584, 0.031916916370391846, 0.0991625189781189, 0.004033073782920837, 0.007390385493636131, 0.0014684813795611262, 0.015356114134192467], "elapsed_s": 1118.5954213142395} {"step": 9300, "train_l1": 0.019489457830786705, "kl": 0.010635627433657646, "validation_action_l1": 0.026154780760407448, "validation_l1_per_dimension": [0.03302325680851936, 0.022023187950253487, 0.08360709249973297, 0.0034510144032537937, 0.007128097116947174, 0.0014954388607293367, 0.03235537186264992], "elapsed_s": 1123.9546287059784} {"step": 9400, "train_l1": 0.011961003765463829, "kl": 0.008865050971508026, "validation_action_l1": 0.023474695160984993, "validation_l1_per_dimension": [0.020019883289933205, 0.02643422596156597, 0.08626767992973328, 0.003357585286721587, 0.007430833764374256, 0.0014968313043937087, 0.01931583136320114], "elapsed_s": 1129.1832139492035} {"step": 9500, "train_l1": 0.009691922925412655, "kl": 0.010947220027446747, "validation_action_l1": 0.027205143123865128, "validation_l1_per_dimension": [0.03516137972474098, 0.03936440125107765, 0.06998006254434586, 0.0032810233533382416, 0.00711513077840209, 0.0015868220943957567, 0.0339471809566021], "elapsed_s": 1134.5164902210236} {"step": 9600, "train_l1": 0.012221924029290676, "kl": 0.003745683468878269, "validation_action_l1": 0.023264676332473755, "validation_l1_per_dimension": [0.030928611755371094, 0.03370717912912369, 0.06647804379463196, 0.0028652886394411325, 0.0052071562968194485, 0.0015839679399505258, 0.022082479670643806], "elapsed_s": 1139.9101071357727} {"step": 9700, "train_l1": 0.010135205462574959, "kl": 0.010641423985362053, "validation_action_l1": 0.020968658849596977, "validation_l1_per_dimension": [0.02694881521165371, 0.037740979343652725, 0.05599348619580269, 0.0028172519523650408, 0.004827472381293774, 0.0016506393440067768, 0.016801947727799416], "elapsed_s": 1145.1618523597717} {"step": 9800, "train_l1": 0.010892588645219803, "kl": 0.008825533092021942, "validation_action_l1": 0.023016395047307014, "validation_l1_per_dimension": [0.03678562864661217, 0.042162977159023285, 0.05813441425561905, 0.0028882818296551704, 0.0046361577697098255, 0.0014070677570998669, 0.015100234188139439], "elapsed_s": 1150.5472948551178} {"step": 9900, "train_l1": 0.011909887194633484, "kl": 0.009448453783988953, "validation_action_l1": 0.022394850850105286, "validation_l1_per_dimension": [0.025602135807275772, 0.02970302477478981, 0.07282272726297379, 0.0028755394741892815, 0.005746269598603249, 0.001383308321237564, 0.018630944192409515], "elapsed_s": 1155.782066822052} {"step": 10000, "train_l1": 0.011444615200161934, "kl": 0.007569441106170416, "validation_action_l1": 0.02759731002151966, "validation_l1_per_dimension": [0.02859511412680149, 0.03861363232135773, 0.10131366550922394, 0.003911301027983427, 0.007903413847088814, 0.0015964321792125702, 0.011247613467276096], "elapsed_s": 1161.0938260555267} {"step": 10100, "train_l1": 0.010509434156119823, "kl": 0.009539743885397911, "validation_action_l1": 0.0269438736140728, "validation_l1_per_dimension": [0.0315529927611351, 0.027105895802378654, 0.0710882619023323, 0.005568202119320631, 0.010409423150122166, 0.0014422200620174408, 0.04144011810421944], "elapsed_s": 1166.763718366623} {"step": 10200, "train_l1": 0.00998913124203682, "kl": 0.0066572679206728935, "validation_action_l1": 0.022814378142356873, "validation_l1_per_dimension": [0.035129450261592865, 0.02156766690313816, 0.07005999982357025, 0.003477308200672269, 0.006384407170116901, 0.001368441735394299, 0.021713368594646454], "elapsed_s": 1172.1678161621094} {"step": 10300, "train_l1": 0.017437603324651718, "kl": 0.009929396212100983, "validation_action_l1": 0.023830067366361618, "validation_l1_per_dimension": [0.03460433706641197, 0.02934892103075981, 0.07116753607988358, 0.0037877706345170736, 0.00740838423371315, 0.001441441592760384, 0.019052084535360336], "elapsed_s": 1177.4835422039032} {"step": 10400, "train_l1": 0.009734719060361385, "kl": 0.009178617037832737, "validation_action_l1": 0.019044876098632812, "validation_l1_per_dimension": [0.023260848596692085, 0.024905549362301826, 0.052548106759786606, 0.002567872405052185, 0.0056127747520804405, 0.001415639417245984, 0.023003336042165756], "elapsed_s": 1182.8880126476288} {"step": 10500, "train_l1": 0.011517585255205631, "kl": 0.010213618166744709, "validation_action_l1": 0.0196368470788002, "validation_l1_per_dimension": [0.02598864585161209, 0.030790844932198524, 0.05892324820160866, 0.0027791569009423256, 0.003948010038584471, 0.0014315046137198806, 0.013596517033874989], "elapsed_s": 1188.1642637252808} {"step": 10600, "train_l1": 0.010873156599700451, "kl": 0.008165942505002022, "validation_action_l1": 0.019589530304074287, "validation_l1_per_dimension": [0.021556571125984192, 0.02863446995615959, 0.06021995469927788, 0.0025056572631001472, 0.004837498534470797, 0.001406508730724454, 0.01796606369316578], "elapsed_s": 1193.4446070194244} {"step": 10700, "train_l1": 0.011214300990104675, "kl": 0.00965228769928217, "validation_action_l1": 0.026163119822740555, "validation_l1_per_dimension": [0.033965110778808594, 0.033377423882484436, 0.09029927849769592, 0.0031616336200386286, 0.005985207390040159, 0.0013748867204412818, 0.014978299848735332], "elapsed_s": 1198.6445450782776} {"step": 10800, "train_l1": 0.010400587692856789, "kl": 0.006833274383097887, "validation_action_l1": 0.021786823868751526, "validation_l1_per_dimension": [0.031762611120939255, 0.040833357721567154, 0.05773413926362991, 0.0032372556161135435, 0.006413113325834274, 0.0015192710561677814, 0.011008025147020817], "elapsed_s": 1203.8997020721436} {"step": 10900, "train_l1": 0.009252146817743778, "kl": 0.009123997762799263, "validation_action_l1": 0.025589238852262497, "validation_l1_per_dimension": [0.02872680500149727, 0.03380145505070686, 0.07814730703830719, 0.003257929580286145, 0.007062864489853382, 0.001518681296147406, 0.026609638705849648], "elapsed_s": 1209.1846115589142} {"step": 11000, "train_l1": 0.01009867712855339, "kl": 0.007229804527014494, "validation_action_l1": 0.030578818172216415, "validation_l1_per_dimension": [0.04730117693543434, 0.040428318083286285, 0.09121286123991013, 0.004274813923984766, 0.008494576439261436, 0.001778629724867642, 0.02056136168539524], "elapsed_s": 1214.6387763023376} {"step": 11100, "train_l1": 0.011585837230086327, "kl": 0.010620027780532837, "validation_action_l1": 0.02028484269976616, "validation_l1_per_dimension": [0.0218542218208313, 0.029970863834023476, 0.06945948302745819, 0.003385139163583517, 0.006504477001726627, 0.0014668136136606336, 0.00935290101915598], "elapsed_s": 1220.2131607532501} {"step": 11200, "train_l1": 0.009798191487789154, "kl": 0.008517242036759853, "validation_action_l1": 0.02146017923951149, "validation_l1_per_dimension": [0.02102160081267357, 0.02274215966463089, 0.07434941828250885, 0.003823871724307537, 0.00822650920599699, 0.0012817278038710356, 0.018775975331664085], "elapsed_s": 1225.3877828121185} {"step": 11300, "train_l1": 0.010158506222069263, "kl": 0.007518155965954065, "validation_action_l1": 0.026575889438390732, "validation_l1_per_dimension": [0.033105771988630295, 0.04036417230963707, 0.08184030652046204, 0.0031662858091294765, 0.0058330814354121685, 0.0016448181122541428, 0.02007678709924221], "elapsed_s": 1230.5973389148712} {"step": 11400, "train_l1": 0.01132890023291111, "kl": 0.00844813883304596, "validation_action_l1": 0.023208104074001312, "validation_l1_per_dimension": [0.02362489327788353, 0.030089331790804863, 0.08532214164733887, 0.0036262909416109324, 0.008029828779399395, 0.001378835877403617, 0.010385404340922832], "elapsed_s": 1235.8434419631958} {"step": 11500, "train_l1": 0.018017204478383064, "kl": 0.007909614592790604, "validation_action_l1": 0.02441992796957493, "validation_l1_per_dimension": [0.025116004049777985, 0.03088611736893654, 0.0803796797990799, 0.003821834921836853, 0.006507374811917543, 0.0013963208766654134, 0.022832173854112625], "elapsed_s": 1241.1323306560516} {"step": 11600, "train_l1": 0.009829864837229252, "kl": 0.009343689307570457, "validation_action_l1": 0.01828467659652233, "validation_l1_per_dimension": [0.02456524781882763, 0.02095216140151024, 0.05569729208946228, 0.0030498988926410675, 0.004754198249429464, 0.0011886742431670427, 0.01778525672852993], "elapsed_s": 1246.3856987953186} {"step": 11700, "train_l1": 0.009990030899643898, "kl": 0.011103441938757896, "validation_action_l1": 0.02641715481877327, "validation_l1_per_dimension": [0.03893056511878967, 0.0381745845079422, 0.07622352987527847, 0.004298919811844826, 0.009225131012499332, 0.0015526504721492529, 0.01651468314230442], "elapsed_s": 1251.479838848114} {"step": 11800, "train_l1": 0.008724959567189217, "kl": 0.009754648432135582, "validation_action_l1": 0.02258184924721718, "validation_l1_per_dimension": [0.030602894723415375, 0.027393411844968796, 0.057339951395988464, 0.002476969501003623, 0.004903942812234163, 0.0014552706852555275, 0.03390049934387207], "elapsed_s": 1256.7592589855194} {"step": 11900, "train_l1": 0.0101581746712327, "kl": 0.009463809430599213, "validation_action_l1": 0.02514861524105072, "validation_l1_per_dimension": [0.02970007061958313, 0.031197136268019676, 0.08990432322025299, 0.003017019247636199, 0.005995169747620821, 0.0012060538865625858, 0.015020527876913548], "elapsed_s": 1261.9197251796722} {"step": 12000, "train_l1": 0.01690014638006687, "kl": 0.006889703217893839, "validation_action_l1": 0.02517739124596119, "validation_l1_per_dimension": [0.020626161247491837, 0.020026467740535736, 0.0921977162361145, 0.0029340980108827353, 0.006001628935337067, 0.0015854145167395473, 0.03287025913596153], "elapsed_s": 1266.9084784984589} {"step": 12100, "train_l1": 0.01112681720405817, "kl": 0.009957591071724892, "validation_action_l1": 0.019473697990179062, "validation_l1_per_dimension": [0.029905157163739204, 0.03165352717041969, 0.05089068040251732, 0.002541015390306711, 0.004792564082890749, 0.001427929033525288, 0.015105004422366619], "elapsed_s": 1272.2876131534576} {"step": 12200, "train_l1": 0.00927925668656826, "kl": 0.00925306137651205, "validation_action_l1": 0.013340282253921032, "validation_l1_per_dimension": [0.015665261074900627, 0.014266196638345718, 0.04667474702000618, 0.002498977119103074, 0.003949095960706472, 0.0012490554945543408, 0.009078647941350937], "elapsed_s": 1277.4133586883545} {"step": 12300, "train_l1": 0.011100486852228642, "kl": 0.011344154365360737, "validation_action_l1": 0.021975077688694, "validation_l1_per_dimension": [0.030527319759130478, 0.022549249231815338, 0.059695929288864136, 0.0028101529460400343, 0.005475572310388088, 0.001146423863247037, 0.031620897352695465], "elapsed_s": 1282.9593441486359} {"step": 12400, "train_l1": 0.01038309559226036, "kl": 0.008859613910317421, "validation_action_l1": 0.020073136314749718, "validation_l1_per_dimension": [0.02353554032742977, 0.030093315988779068, 0.0598767064511776, 0.00393358850851655, 0.0070274947211146355, 0.0013425330398604274, 0.014702781103551388], "elapsed_s": 1297.807434797287} {"step": 12500, "train_l1": 0.010057647712528706, "kl": 0.013301551342010498, "validation_action_l1": 0.02086387388408184, "validation_l1_per_dimension": [0.027326257899403572, 0.028325989842414856, 0.06040498614311218, 0.002992238849401474, 0.004671458154916763, 0.001180785009637475, 0.0211454126983881], "elapsed_s": 1323.3273286819458} {"step": 12600, "train_l1": 0.010242009535431862, "kl": 0.010226276703178883, "validation_action_l1": 0.017618317157030106, "validation_l1_per_dimension": [0.024083206430077553, 0.01739892177283764, 0.05449357256293297, 0.002899711951613426, 0.005864434409886599, 0.0014934635255485773, 0.017094913870096207], "elapsed_s": 1347.8679826259613} {"step": 12700, "train_l1": 0.010661933571100235, "kl": 0.010779689997434616, "validation_action_l1": 0.018045401200652122, "validation_l1_per_dimension": [0.019358662888407707, 0.021221362054347992, 0.058447811752557755, 0.0027083398308604956, 0.005833341274410486, 0.001182994688861072, 0.017565295100212097], "elapsed_s": 1370.0105922222137} {"step": 12800, "train_l1": 0.009036657400429249, "kl": 0.011423803865909576, "validation_action_l1": 0.02392026223242283, "validation_l1_per_dimension": [0.02815815433859825, 0.0340571403503418, 0.07613319903612137, 0.002322578337043524, 0.004971609916538, 0.0013710730709135532, 0.02042808011174202], "elapsed_s": 1393.5101742744446} {"step": 12900, "train_l1": 0.008749342523515224, "kl": 0.008583588525652885, "validation_action_l1": 0.02343623898923397, "validation_l1_per_dimension": [0.03467739373445511, 0.026483073830604553, 0.07215408235788345, 0.0034790069330483675, 0.00591292092576623, 0.0014202477177605033, 0.019926955923438072], "elapsed_s": 1416.771677494049} {"step": 13000, "train_l1": 0.009174036793410778, "kl": 0.00871681235730648, "validation_action_l1": 0.020121393725275993, "validation_l1_per_dimension": [0.017467251047492027, 0.019722051918506622, 0.07200723141431808, 0.0043969121761620045, 0.009190223179757595, 0.0012298441724851727, 0.01683623716235161], "elapsed_s": 1439.8639075756073} {"step": 13100, "train_l1": 0.009023255668580532, "kl": 0.011845308355987072, "validation_action_l1": 0.022538701072335243, "validation_l1_per_dimension": [0.02781698852777481, 0.027012459933757782, 0.07369523495435715, 0.002143658697605133, 0.004170428495854139, 0.001259182346984744, 0.02167295478284359], "elapsed_s": 1463.6062989234924} {"step": 13200, "train_l1": 0.00966867245733738, "kl": 0.013394827954471111, "validation_action_l1": 0.019219795241951942, "validation_l1_per_dimension": [0.01990969106554985, 0.02671472169458866, 0.07157103717327118, 0.0030245527159422636, 0.005800135433673859, 0.0011951514752581716, 0.006323282606899738], "elapsed_s": 1487.0339741706848} {"step": 13300, "train_l1": 0.011780335567891598, "kl": 0.012471401132643223, "validation_action_l1": 0.02087303437292576, "validation_l1_per_dimension": [0.03244698420166969, 0.021288298070430756, 0.05566658824682236, 0.002684323349967599, 0.005526190157979727, 0.0012176049640402198, 0.02728124149143696], "elapsed_s": 1511.3116147518158} {"step": 13400, "train_l1": 0.008902435190975666, "kl": 0.009930642321705818, "validation_action_l1": 0.027046537026762962, "validation_l1_per_dimension": [0.035147637128829956, 0.038779303431510925, 0.08295432478189468, 0.003952889237552881, 0.007610459811985493, 0.0013097613118588924, 0.01957138068974018], "elapsed_s": 1535.3050329685211} {"step": 13500, "train_l1": 0.00969022698700428, "kl": 0.008515718393027782, "validation_action_l1": 0.02432662807404995, "validation_l1_per_dimension": [0.036932021379470825, 0.0464155450463295, 0.05811984837055206, 0.002290288917720318, 0.004515205044299364, 0.0012549383100122213, 0.02075854130089283], "elapsed_s": 1558.7412300109863} {"step": 13600, "train_l1": 0.010027371346950531, "kl": 0.01282269787043333, "validation_action_l1": 0.02676369436085224, "validation_l1_per_dimension": [0.04020372033119202, 0.029446778818964958, 0.07960707694292068, 0.0026934694033116102, 0.005417899694293737, 0.0013449537800624967, 0.028631962835788727], "elapsed_s": 1583.7947113513947} {"step": 13700, "train_l1": 0.014857388101518154, "kl": 0.010469176806509495, "validation_action_l1": 0.024177467450499535, "validation_l1_per_dimension": [0.031168052926659584, 0.033314745873212814, 0.07347633689641953, 0.0028200186789035797, 0.006132397335022688, 0.0011849640868604183, 0.021145759150385857], "elapsed_s": 1605.8756761550903} {"step": 13800, "train_l1": 0.010211150161921978, "kl": 0.010114792734384537, "validation_action_l1": 0.025200901553034782, "validation_l1_per_dimension": [0.036971867084503174, 0.04043647274374962, 0.05920914188027382, 0.0030260905623435974, 0.005619365721940994, 0.0012576825683936477, 0.029885679483413696], "elapsed_s": 1612.1853034496307} {"step": 13900, "train_l1": 0.009854387491941452, "kl": 0.010558958165347576, "validation_action_l1": 0.019439617171883583, "validation_l1_per_dimension": [0.018751269206404686, 0.022828055545687675, 0.0654972493648529, 0.0031068299431353807, 0.006012437399476767, 0.001103613874875009, 0.01877785474061966], "elapsed_s": 1617.3840854167938} {"step": 14000, "train_l1": 0.010799462907016277, "kl": 0.013415493071079254, "validation_action_l1": 0.02169458009302616, "validation_l1_per_dimension": [0.028484275564551353, 0.023216044530272484, 0.07527200877666473, 0.0035447105765342712, 0.0069015673361718655, 0.0011648567160591483, 0.013278612866997719], "elapsed_s": 1622.5858652591705} {"step": 14100, "train_l1": 0.009256833232939243, "kl": 0.012029992416501045, "validation_action_l1": 0.017784494906663895, "validation_l1_per_dimension": [0.030990928411483765, 0.02773210033774376, 0.0492926724255085, 0.00226730783469975, 0.003764852648600936, 0.0011271104449406266, 0.00931648351252079], "elapsed_s": 1628.046961069107} {"step": 14200, "train_l1": 0.01020030863583088, "kl": 0.005671877413988113, "validation_action_l1": 0.01519407145678997, "validation_l1_per_dimension": [0.025583317503333092, 0.023437796160578728, 0.03912676125764847, 0.002490759827196598, 0.0039481790736317635, 0.0012091570533812046, 0.010562525130808353], "elapsed_s": 1633.2492685317993} {"step": 14300, "train_l1": 0.00863366574048996, "kl": 0.016285575926303864, "validation_action_l1": 0.023827357217669487, "validation_l1_per_dimension": [0.038001157343387604, 0.03847088664770126, 0.06804808229207993, 0.0031725771259516478, 0.006163999438285828, 0.0013584343250840902, 0.011576367542147636], "elapsed_s": 1638.469111919403} {"step": 14400, "train_l1": 0.007742688525468111, "kl": 0.01956522837281227, "validation_action_l1": 0.02387513592839241, "validation_l1_per_dimension": [0.03119814023375511, 0.025818580761551857, 0.0833813026547432, 0.0035301940515637398, 0.007513914257287979, 0.0013024043291807175, 0.01438140869140625], "elapsed_s": 1643.677122592926} {"step": 14500, "train_l1": 0.010788332670927048, "kl": 0.005445970222353935, "validation_action_l1": 0.020150557160377502, "validation_l1_per_dimension": [0.0331304706633091, 0.02211613766849041, 0.053356654942035675, 0.0034975705202668905, 0.006448773201555014, 0.001513191033154726, 0.020991094410419464], "elapsed_s": 1648.9370510578156} {"step": 14600, "train_l1": 0.01016048900783062, "kl": 0.014182464219629765, "validation_action_l1": 0.02450353093445301, "validation_l1_per_dimension": [0.023647435009479523, 0.01844041794538498, 0.07515134662389755, 0.004809353034943342, 0.01027075294405222, 0.0009973179548978806, 0.03820810467004776], "elapsed_s": 1653.9923899173737} {"step": 14700, "train_l1": 0.008603179827332497, "kl": 0.013073517009615898, "validation_action_l1": 0.02497091144323349, "validation_l1_per_dimension": [0.03261790797114372, 0.03259207680821419, 0.07219497859477997, 0.0032762379851192236, 0.00756846321746707, 0.0011664355406537652, 0.02538028173148632], "elapsed_s": 1659.2022876739502} {"step": 14800, "train_l1": 0.008659516461193562, "kl": 0.00847240723669529, "validation_action_l1": 0.016166705638170242, "validation_l1_per_dimension": [0.016621965914964676, 0.017493654042482376, 0.0573662593960762, 0.002429884159937501, 0.0048682233318686485, 0.0009894048562273383, 0.013397551141679287], "elapsed_s": 1664.5217356681824} {"step": 14900, "train_l1": 0.008364683948457241, "kl": 0.014494195580482483, "validation_action_l1": 0.02237044833600521, "validation_l1_per_dimension": [0.023436611518263817, 0.029197590425610542, 0.07712411135435104, 0.0029579601250588894, 0.005863305181264877, 0.0013044183142483234, 0.016709139570593834], "elapsed_s": 1669.7512505054474} {"step": 15000, "train_l1": 0.010238495655357838, "kl": 0.008213287219405174, "validation_action_l1": 0.025923117995262146, "validation_l1_per_dimension": [0.037939656525850296, 0.036256495863199234, 0.07198546081781387, 0.0025647073052823544, 0.005516190081834793, 0.0012687460985034704, 0.025930562987923622], "elapsed_s": 1674.988314628601}