Small bug fixed in nl_mpsc

experiments/mpsc/models/rl_models/quadrotor_3D/track/ppo/mpsf_sr_pen_1/seed_4077/config.yaml

@@ -25,7 +25,6 @@ algo_config:
   num_workers: 1
   opt_epochs: 20
   penalize_sf_diff: true
-  pretrained: ./models/rl_models/quadrotor_3D/track/ppo_pretrain/seed_4077/
   rollout_batch_size: 1
   rollout_steps: 1000
   save_interval: 0
@@ -49,10 +48,11 @@ kv_overrides:
 - algo_config.use_safe_reset=True
 - algo_config.penalize_sf_diff=True
 - algo_config.sf_penalty=1
-- algo_config.pretrained=./models/rl_models/quadrotor_3D/track/ppo_pretrain/seed_4077/
 - task_config.seed=4077
 - algo_config.seed=4077
 - sf_config.seed=4077
+logging:
+  total_learning_time: 19853.810920000076
 output_dir: ./models/rl_models/quadrotor_3D/track/ppo/mpsf_sr_pen_1/seed_4077/
 overrides:
 - ./config_overrides/quadrotor_3D/ppo_quadrotor_3D.yaml

experiments/mpsc/models/rl_models/quadrotor_3D/track/ppo/mpsf_sr_pen_1/seed_4077/logs/loss/approx_kl.log

@@ -1,101 +1,101 @@
 step,loss/approx_kl
-10000,0.029208557703532277
-20000,0.032586767640896144
-30000,0.025630848994478584
-40000,0.018259687620835997
-50000,0.011078280257061124
-60000,0.01784560952801257
-70000,0.028387357271276413
-80000,0.014744772606839738
-90000,0.022554900233323374
-100000,0.03381081408200164
-110000,0.021157057660942273
-120000,0.012980545591562986
-130000,0.01448677368462086
-140000,0.01618971132362882
-150000,0.027147181704640387
-160000,0.03227456621825696
-170000,0.028502518093834327
-180000,0.03360094296125075
-190000,0.02035950571298599
-200000,0.030597594985738396
-210000,0.029150963341817254
-220000,0.021370276901870967
-230000,0.026677678882454835
-240000,0.02569064134731889
-250000,0.023797816317528486
-260000,0.03238879423588514
-270000,0.03242140817455947
-280000,0.029922109438727296
-290000,0.02502187010832131
-300000,0.025891695031896235
-310000,0.03266000323928893
-320000,0.020521501762171584
-330000,0.0321559206272165
-340000,0.03273177132941782
-350000,0.02074912659203013
-360000,0.021280657981211943
-370000,0.026237463330229128
-380000,0.024662876967340704
-390000,0.028879422973841433
-400000,0.03003662669410308
-410000,0.028840302008514607
-420000,0.027182075738285977
-430000,0.022763655552019674
-440000,0.031080836523324246
-450000,0.027716765382016693
-460000,0.03432357050478459
-470000,0.023513463124011955
-480000,0.015433562810843187
-490000,0.03728839297158022
-500000,0.02360844494154056
-510000,0.03617782692114512
-520000,0.029703678097575903
-530000,0.03617854948776463
-540000,0.03279251842759549
-550000,0.02574667798665663
-560000,0.03175092145490149
-570000,0.024243962081770105
-580000,0.03132888713541131
-590000,0.0228570561700811
-600000,0.0334127701818943
-610000,0.03893137550912798
-620000,0.03610405530780554
-630000,0.020595745866497362
-640000,0.024008269033705194
-650000,0.021521438083921866
-660000,0.030270544004937016
-670000,0.027262707939371474
-680000,0.02819207076293726
-690000,0.02912460401033362
-700000,0.027005492011085153
-710000,0.02883505852272113
-720000,0.01758278487250209
-730000,0.02539473500413199
-740000,0.023108853834370773
-750000,0.03146429948198299
-760000,0.02944188287171225
-770000,0.023764610554402075
-780000,0.015817845379933713
-790000,0.029224518127739428
-800000,0.03301882237816851
-810000,0.01593577017386754
-820000,0.01645373026840389
-830000,0.021518756107737624
-840000,0.02098657254440089
-850000,0.013631100362787644
-860000,0.021790609570840995
-870000,0.016325075551867487
-880000,0.031860177777707575
-890000,0.028470443344364566
-900000,0.020560097849617404
-910000,0.028620055193702382
-920000,0.020117931657781203
-930000,0.008297148657341798
-940000,0.028316706574211516
-950000,0.03018105545391639
-960000,0.017713127906123796
-970000,0.03288293123866121
-980000,0.014923745207488537
-990000,0.02158841568355759
-1000000,0.025475860014557834
+10000,0.027778915734961624
+20000,0.011920045906056961
+30000,0.022770270379260184
+40000,0.027563783146130543
+50000,0.030970997503027325
+60000,0.02065028810563187
+70000,0.03478063237853349
+80000,0.0207850004080683
+90000,0.02556394076285263
+100000,0.017919961983958878
+110000,0.019842859574904042
+120000,0.03039515113147596
+130000,0.030615829893698293
+140000,0.0236469846063604
+150000,0.03170254800158243
+160000,0.019154382636770603
+170000,0.029730018383512895
+180000,0.03456262424588204
+190000,0.024127350887283683
+200000,0.0208336564557006
+210000,0.021095521701499816
+220000,0.0322838061178724
+230000,0.021422489654893673
+240000,0.026789182921250664
+250000,0.01985148958240946
+260000,0.018930455793937047
+270000,0.018050395464524624
+280000,0.028094121751685942
+290000,0.023556562901164098
+300000,0.02079606312327087
+310000,0.02183036467370887
+320000,0.026412193989381196
+330000,0.034681907311702766
+340000,0.022931590133036178
+350000,0.02771437927149236
+360000,0.03713707230053842
+370000,0.024188099242746827
+380000,0.02103266377622882
+390000,0.0372461565459768
+400000,0.026820074689264096
+410000,0.020573528887083133
+420000,0.03038510410115123
+430000,0.029062136417875688
+440000,0.023465152736753224
+450000,0.01921436528985699
+460000,0.03741470061553022
+470000,0.02811832030614217
+480000,0.0312755671950678
+490000,0.028572570579126478
+500000,0.028399945935234434
+510000,0.01797542811060945
+520000,0.026582096703350544
+530000,0.029829027410596613
+540000,0.01241887230426073
+550000,0.016032927095269163
+560000,0.027915811724960805
+570000,0.0317278249344478
+580000,0.040940430077413714
+590000,0.026106951137383778
+600000,0.01947905501971642
+610000,0.015671628154814245
+620000,0.024176539403075976
+630000,0.01658071631876131
+640000,0.029594388386855526
+650000,0.012564927029112974
+660000,0.011058986218025285
+670000,0.014169181588416296
+680000,0.02792811232308547
+690000,0.02891999964291851
+700000,0.018978109955787657
+710000,0.01858787651484211
+720000,0.018367637631793818
+730000,0.03774916296824812
+740000,0.03114891167109211
+750000,0.01705709972108404
+760000,0.027076383555928868
+770000,0.02275712365905444
+780000,0.031039722884694733
+790000,0.031862552867581447
+800000,0.037632742710411546
+810000,0.021646718525638185
+820000,0.03239857172593474
+830000,0.03660221661751469
+840000,0.02637914527828495
+850000,0.019051578578849634
+860000,0.018982918684681258
+870000,0.010516501528521379
+880000,0.035051878200223055
+890000,0.011275681791206199
+900000,0.020837759226560594
+910000,0.024735974023739497
+920000,0.029985250532627107
+930000,0.025630753207951783
+940000,0.021290472677598395
+950000,0.02104105018079281
+960000,0.025920864939689637
+970000,0.015077712417890628
+980000,0.023138111177831894
+990000,0.025282644449422752
+1000000,0.024343484515945115