alidenewade commited on
Commit
d3d10ea
·
verified ·
1 Parent(s): 35d3de9

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. replay.mp4 +2 -2
  3. sf_log.txt +629 -0
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 4.11 +/- 0.62
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 4.07 +/- 0.70
19
  name: mean_reward
20
  verified: false
21
  ---
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef772052cb02b4cbc305fa9b5a87a7f155a919d2d3d71db999a9133eaffd10d5
3
- size 63660637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b800b24655a949eb854d52221fcae684e142841d25dc693d343231d6d13d9f32
3
+ size 63879708
sf_log.txt CHANGED
@@ -36159,3 +36159,632 @@ main_loop: 29019.2188
36159
  [2024-11-08 07:23:22,827][41694] Avg episode rewards: #0: 4.604, true rewards: #0: 4.114
36160
  [2024-11-08 07:23:22,829][41694] Avg episode reward: 4.604, avg true_objective: 4.114
36161
  [2024-11-08 07:25:09,068][41694] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36159
  [2024-11-08 07:23:22,827][41694] Avg episode rewards: #0: 4.604, true rewards: #0: 4.114
36160
  [2024-11-08 07:23:22,829][41694] Avg episode reward: 4.604, avg true_objective: 4.114
36161
  [2024-11-08 07:25:09,068][41694] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
36162
+ [2024-11-08 07:25:55,668][41694] The model has been pushed to https://huggingface.co/alidenewade/rl_course_vizdoom_health_gathering_supreme-alid
36163
+ [2024-11-08 07:29:58,984][41694] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
36164
+ [2024-11-08 07:29:58,986][41694] Overriding arg 'num_workers' with value 1 passed from command line
36165
+ [2024-11-08 07:29:58,987][41694] Adding new argument 'no_render'=True that is not in the saved config file!
36166
+ [2024-11-08 07:29:58,988][41694] Adding new argument 'save_video'=True that is not in the saved config file!
36167
+ [2024-11-08 07:29:58,992][41694] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
36168
+ [2024-11-08 07:29:58,995][41694] Adding new argument 'video_name'=None that is not in the saved config file!
36169
+ [2024-11-08 07:29:58,996][41694] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
36170
+ [2024-11-08 07:29:58,998][41694] Adding new argument 'max_num_episodes'=100 that is not in the saved config file!
36171
+ [2024-11-08 07:29:58,999][41694] Adding new argument 'push_to_hub'=True that is not in the saved config file!
36172
+ [2024-11-08 07:29:59,002][41694] Adding new argument 'hf_repository'='alidenewade/rl_course_vizdoom_health_gathering_supreme-alid' that is not in the saved config file!
36173
+ [2024-11-08 07:29:59,003][41694] Adding new argument 'policy_index'=0 that is not in the saved config file!
36174
+ [2024-11-08 07:29:59,006][41694] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
36175
+ [2024-11-08 07:29:59,007][41694] Adding new argument 'train_script'=None that is not in the saved config file!
36176
+ [2024-11-08 07:29:59,009][41694] Adding new argument 'enjoy_script'=None that is not in the saved config file!
36177
+ [2024-11-08 07:29:59,012][41694] Using frameskip 1 and render_action_repeat=4 for evaluation
36178
+ [2024-11-08 07:29:59,101][41694] RunningMeanStd input shape: (3, 72, 128)
36179
+ [2024-11-08 07:29:59,160][41694] RunningMeanStd input shape: (1,)
36180
+ [2024-11-08 07:29:59,257][41694] ConvEncoder: input_channels=3
36181
+ [2024-11-08 07:29:59,321][41694] Conv encoder output size: 512
36182
+ [2024-11-08 07:29:59,323][41694] Policy head output size: 512
36183
+ [2024-11-08 07:30:00,646][41694] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000052658_215687168.pth...
36184
+ [2024-11-08 07:30:01,794][41694] Num frames 100...
36185
+ [2024-11-08 07:30:02,261][41694] Num frames 200...
36186
+ [2024-11-08 07:30:02,708][41694] Num frames 300...
36187
+ [2024-11-08 07:30:03,173][41694] Num frames 400...
36188
+ [2024-11-08 07:30:03,398][41694] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
36189
+ [2024-11-08 07:30:03,401][41694] Avg episode reward: 5.480, avg true_objective: 4.480
36190
+ [2024-11-08 07:30:03,546][41694] Num frames 500...
36191
+ [2024-11-08 07:30:03,816][41694] Num frames 600...
36192
+ [2024-11-08 07:30:04,059][41694] Num frames 700...
36193
+ [2024-11-08 07:30:04,126][41694] Avg episode rewards: #0: 4.020, true rewards: #0: 3.520
36194
+ [2024-11-08 07:30:04,129][41694] Avg episode reward: 4.020, avg true_objective: 3.520
36195
+ [2024-11-08 07:30:04,372][41694] Num frames 800...
36196
+ [2024-11-08 07:30:04,594][41694] Num frames 900...
36197
+ [2024-11-08 07:30:04,834][41694] Num frames 1000...
36198
+ [2024-11-08 07:30:05,100][41694] Num frames 1100...
36199
+ [2024-11-08 07:30:05,293][41694] Avg episode rewards: #0: 4.507, true rewards: #0: 3.840
36200
+ [2024-11-08 07:30:05,297][41694] Avg episode reward: 4.507, avg true_objective: 3.840
36201
+ [2024-11-08 07:30:05,452][41694] Num frames 1200...
36202
+ [2024-11-08 07:30:05,755][41694] Num frames 1300...
36203
+ [2024-11-08 07:30:06,055][41694] Num frames 1400...
36204
+ [2024-11-08 07:30:06,313][41694] Num frames 1500...
36205
+ [2024-11-08 07:30:06,455][41694] Avg episode rewards: #0: 4.340, true rewards: #0: 3.840
36206
+ [2024-11-08 07:30:06,457][41694] Avg episode reward: 4.340, avg true_objective: 3.840
36207
+ [2024-11-08 07:30:06,640][41694] Num frames 1600...
36208
+ [2024-11-08 07:30:06,922][41694] Num frames 1700...
36209
+ [2024-11-08 07:30:07,167][41694] Num frames 1800...
36210
+ [2024-11-08 07:30:07,446][41694] Num frames 1900...
36211
+ [2024-11-08 07:30:07,564][41694] Avg episode rewards: #0: 4.240, true rewards: #0: 3.840
36212
+ [2024-11-08 07:30:07,566][41694] Avg episode reward: 4.240, avg true_objective: 3.840
36213
+ [2024-11-08 07:30:07,826][41694] Num frames 2000...
36214
+ [2024-11-08 07:30:08,037][41694] Num frames 2100...
36215
+ [2024-11-08 07:30:08,261][41694] Num frames 2200...
36216
+ [2024-11-08 07:30:08,459][41694] Num frames 2300...
36217
+ [2024-11-08 07:30:08,657][41694] Avg episode rewards: #0: 4.447, true rewards: #0: 3.947
36218
+ [2024-11-08 07:30:08,660][41694] Avg episode reward: 4.447, avg true_objective: 3.947
36219
+ [2024-11-08 07:30:08,736][41694] Num frames 2400...
36220
+ [2024-11-08 07:30:09,234][41694] Num frames 2500...
36221
+ [2024-11-08 07:30:09,830][41694] Num frames 2600...
36222
+ [2024-11-08 07:30:10,227][41694] Num frames 2700...
36223
+ [2024-11-08 07:30:10,689][41694] Avg episode rewards: #0: 4.360, true rewards: #0: 3.931
36224
+ [2024-11-08 07:30:10,691][41694] Avg episode reward: 4.360, avg true_objective: 3.931
36225
+ [2024-11-08 07:30:10,944][41694] Num frames 2800...
36226
+ [2024-11-08 07:30:11,284][41694] Num frames 2900...
36227
+ [2024-11-08 07:30:11,598][41694] Num frames 3000...
36228
+ [2024-11-08 07:30:11,890][41694] Num frames 3100...
36229
+ [2024-11-08 07:30:12,154][41694] Num frames 3200...
36230
+ [2024-11-08 07:30:12,397][41694] Num frames 3300...
36231
+ [2024-11-08 07:30:12,622][41694] Num frames 3400...
36232
+ [2024-11-08 07:30:12,749][41694] Avg episode rewards: #0: 5.155, true rewards: #0: 4.280
36233
+ [2024-11-08 07:30:12,752][41694] Avg episode reward: 5.155, avg true_objective: 4.280
36234
+ [2024-11-08 07:30:13,067][41694] Num frames 3500...
36235
+ [2024-11-08 07:30:13,472][41694] Num frames 3600...
36236
+ [2024-11-08 07:30:13,886][41694] Num frames 3700...
36237
+ [2024-11-08 07:30:14,302][41694] Num frames 3800...
36238
+ [2024-11-08 07:30:14,407][41694] Avg episode rewards: #0: 5.009, true rewards: #0: 4.231
36239
+ [2024-11-08 07:30:14,409][41694] Avg episode reward: 5.009, avg true_objective: 4.231
36240
+ [2024-11-08 07:30:15,032][41694] Num frames 3900...
36241
+ [2024-11-08 07:30:15,484][41694] Num frames 4000...
36242
+ [2024-11-08 07:30:15,808][41694] Avg episode rewards: #0: 4.764, true rewards: #0: 4.064
36243
+ [2024-11-08 07:30:15,810][41694] Avg episode reward: 4.764, avg true_objective: 4.064
36244
+ [2024-11-08 07:30:15,940][41694] Num frames 4100...
36245
+ [2024-11-08 07:30:16,375][41694] Num frames 4200...
36246
+ [2024-11-08 07:30:16,715][41694] Num frames 4300...
36247
+ [2024-11-08 07:30:17,063][41694] Num frames 4400...
36248
+ [2024-11-08 07:30:17,328][41694] Avg episode rewards: #0: 4.680, true rewards: #0: 4.044
36249
+ [2024-11-08 07:30:17,330][41694] Avg episode reward: 4.680, avg true_objective: 4.044
36250
+ [2024-11-08 07:30:17,487][41694] Num frames 4500...
36251
+ [2024-11-08 07:30:17,776][41694] Num frames 4600...
36252
+ [2024-11-08 07:30:18,342][41694] Num frames 4700...
36253
+ [2024-11-08 07:30:18,855][41694] Num frames 4800...
36254
+ [2024-11-08 07:30:19,598][41694] Avg episode rewards: #0: 4.747, true rewards: #0: 4.080
36255
+ [2024-11-08 07:30:19,599][41694] Avg episode reward: 4.747, avg true_objective: 4.080
36256
+ [2024-11-08 07:30:19,617][41694] Num frames 4900...
36257
+ [2024-11-08 07:30:20,028][41694] Num frames 5000...
36258
+ [2024-11-08 07:30:20,361][41694] Num frames 5100...
36259
+ [2024-11-08 07:30:20,855][41694] Num frames 5200...
36260
+ [2024-11-08 07:30:21,155][41694] Avg episode rewards: #0: 4.677, true rewards: #0: 4.062
36261
+ [2024-11-08 07:30:21,157][41694] Avg episode reward: 4.677, avg true_objective: 4.062
36262
+ [2024-11-08 07:30:21,280][41694] Num frames 5300...
36263
+ [2024-11-08 07:30:21,890][41694] Num frames 5400...
36264
+ [2024-11-08 07:30:22,236][41694] Num frames 5500...
36265
+ [2024-11-08 07:30:22,727][41694] Num frames 5600...
36266
+ [2024-11-08 07:30:23,395][41694] Num frames 5700...
36267
+ [2024-11-08 07:30:23,652][41694] Avg episode rewards: #0: 4.734, true rewards: #0: 4.091
36268
+ [2024-11-08 07:30:23,654][41694] Avg episode reward: 4.734, avg true_objective: 4.091
36269
+ [2024-11-08 07:30:23,917][41694] Num frames 5800...
36270
+ [2024-11-08 07:30:24,254][41694] Num frames 5900...
36271
+ [2024-11-08 07:30:24,621][41694] Num frames 6000...
36272
+ [2024-11-08 07:30:25,052][41694] Num frames 6100...
36273
+ [2024-11-08 07:30:25,172][41694] Avg episode rewards: #0: 4.675, true rewards: #0: 4.075
36274
+ [2024-11-08 07:30:25,175][41694] Avg episode reward: 4.675, avg true_objective: 4.075
36275
+ [2024-11-08 07:30:25,556][41694] Num frames 6200...
36276
+ [2024-11-08 07:30:25,913][41694] Num frames 6300...
36277
+ [2024-11-08 07:30:26,321][41694] Num frames 6400...
36278
+ [2024-11-08 07:30:26,719][41694] Avg episode rewards: #0: 4.623, true rewards: #0: 4.060
36279
+ [2024-11-08 07:30:26,722][41694] Avg episode reward: 4.623, avg true_objective: 4.060
36280
+ [2024-11-08 07:30:26,747][41694] Num frames 6500...
36281
+ [2024-11-08 07:30:27,067][41694] Num frames 6600...
36282
+ [2024-11-08 07:30:27,268][41694] Num frames 6700...
36283
+ [2024-11-08 07:30:27,583][41694] Num frames 6800...
36284
+ [2024-11-08 07:30:27,963][41694] Avg episode rewards: #0: 4.576, true rewards: #0: 4.047
36285
+ [2024-11-08 07:30:27,966][41694] Avg episode reward: 4.576, avg true_objective: 4.047
36286
+ [2024-11-08 07:30:28,077][41694] Num frames 6900...
36287
+ [2024-11-08 07:30:28,659][41694] Num frames 7000...
36288
+ [2024-11-08 07:30:28,953][41694] Num frames 7100...
36289
+ [2024-11-08 07:30:29,073][41694] Avg episode rewards: #0: 4.464, true rewards: #0: 3.964
36290
+ [2024-11-08 07:30:29,078][41694] Avg episode reward: 4.464, avg true_objective: 3.964
36291
+ [2024-11-08 07:30:29,222][41694] Num frames 7200...
36292
+ [2024-11-08 07:30:29,397][41694] Num frames 7300...
36293
+ [2024-11-08 07:30:29,597][41694] Num frames 7400...
36294
+ [2024-11-08 07:30:29,767][41694] Num frames 7500...
36295
+ [2024-11-08 07:30:30,016][41694] Avg episode rewards: #0: 4.518, true rewards: #0: 3.992
36296
+ [2024-11-08 07:30:30,020][41694] Avg episode reward: 4.518, avg true_objective: 3.992
36297
+ [2024-11-08 07:30:30,083][41694] Num frames 7600...
36298
+ [2024-11-08 07:30:30,289][41694] Num frames 7700...
36299
+ [2024-11-08 07:30:30,670][41694] Num frames 7800...
36300
+ [2024-11-08 07:30:31,036][41694] Num frames 7900...
36301
+ [2024-11-08 07:30:31,233][41694] Avg episode rewards: #0: 4.484, true rewards: #0: 3.984
36302
+ [2024-11-08 07:30:31,238][41694] Avg episode reward: 4.484, avg true_objective: 3.984
36303
+ [2024-11-08 07:30:31,322][41694] Num frames 8000...
36304
+ [2024-11-08 07:30:31,530][41694] Num frames 8100...
36305
+ [2024-11-08 07:30:31,743][41694] Num frames 8200...
36306
+ [2024-11-08 07:30:32,005][41694] Num frames 8300...
36307
+ [2024-11-08 07:30:32,129][41694] Avg episode rewards: #0: 4.486, true rewards: #0: 3.962
36308
+ [2024-11-08 07:30:32,131][41694] Avg episode reward: 4.486, avg true_objective: 3.962
36309
+ [2024-11-08 07:30:32,407][41694] Num frames 8400...
36310
+ [2024-11-08 07:30:32,650][41694] Num frames 8500...
36311
+ [2024-11-08 07:30:32,902][41694] Num frames 8600...
36312
+ [2024-11-08 07:30:33,191][41694] Num frames 8700...
36313
+ [2024-11-08 07:30:33,452][41694] Avg episode rewards: #0: 4.531, true rewards: #0: 3.985
36314
+ [2024-11-08 07:30:33,455][41694] Avg episode reward: 4.531, avg true_objective: 3.985
36315
+ [2024-11-08 07:30:33,557][41694] Num frames 8800...
36316
+ [2024-11-08 07:30:33,736][41694] Num frames 8900...
36317
+ [2024-11-08 07:30:33,941][41694] Num frames 9000...
36318
+ [2024-11-08 07:30:34,125][41694] Num frames 9100...
36319
+ [2024-11-08 07:30:34,291][41694] Num frames 9200...
36320
+ [2024-11-08 07:30:34,380][41694] Avg episode rewards: #0: 4.572, true rewards: #0: 4.007
36321
+ [2024-11-08 07:30:34,385][41694] Avg episode reward: 4.572, avg true_objective: 4.007
36322
+ [2024-11-08 07:30:34,557][41694] Num frames 9300...
36323
+ [2024-11-08 07:30:34,735][41694] Num frames 9400...
36324
+ [2024-11-08 07:30:34,996][41694] Avg episode rewards: #0: 4.488, true rewards: #0: 3.947
36325
+ [2024-11-08 07:30:35,000][41694] Avg episode reward: 4.488, avg true_objective: 3.947
36326
+ [2024-11-08 07:30:35,083][41694] Num frames 9500...
36327
+ [2024-11-08 07:30:35,267][41694] Num frames 9600...
36328
+ [2024-11-08 07:30:35,436][41694] Num frames 9700...
36329
+ [2024-11-08 07:30:35,716][41694] Num frames 9800...
36330
+ [2024-11-08 07:30:35,907][41694] Num frames 9900...
36331
+ [2024-11-08 07:30:36,097][41694] Num frames 10000...
36332
+ [2024-11-08 07:30:36,387][41694] Num frames 10100...
36333
+ [2024-11-08 07:30:36,633][41694] Avg episode rewards: #0: 4.750, true rewards: #0: 4.070
36334
+ [2024-11-08 07:30:36,638][41694] Avg episode reward: 4.750, avg true_objective: 4.070
36335
+ [2024-11-08 07:30:36,713][41694] Num frames 10200...
36336
+ [2024-11-08 07:30:37,163][41694] Num frames 10300...
36337
+ [2024-11-08 07:30:37,639][41694] Num frames 10400...
36338
+ [2024-11-08 07:30:37,867][41694] Num frames 10500...
36339
+ [2024-11-08 07:30:38,078][41694] Avg episode rewards: #0: 4.715, true rewards: #0: 4.062
36340
+ [2024-11-08 07:30:38,080][41694] Avg episode reward: 4.715, avg true_objective: 4.062
36341
+ [2024-11-08 07:30:38,194][41694] Num frames 10600...
36342
+ [2024-11-08 07:30:38,496][41694] Num frames 10700...
36343
+ [2024-11-08 07:30:38,768][41694] Num frames 10800...
36344
+ [2024-11-08 07:30:38,861][41694] Avg episode rewards: #0: 4.636, true rewards: #0: 4.006
36345
+ [2024-11-08 07:30:38,863][41694] Avg episode reward: 4.636, avg true_objective: 4.006
36346
+ [2024-11-08 07:30:39,120][41694] Num frames 10900...
36347
+ [2024-11-08 07:30:39,539][41694] Num frames 11000...
36348
+ [2024-11-08 07:30:39,828][41694] Num frames 11100...
36349
+ [2024-11-08 07:30:40,118][41694] Num frames 11200...
36350
+ [2024-11-08 07:30:40,418][41694] Num frames 11300...
36351
+ [2024-11-08 07:30:40,661][41694] Avg episode rewards: #0: 4.736, true rewards: #0: 4.057
36352
+ [2024-11-08 07:30:40,664][41694] Avg episode reward: 4.736, avg true_objective: 4.057
36353
+ [2024-11-08 07:30:40,828][41694] Num frames 11400...
36354
+ [2024-11-08 07:30:41,164][41694] Num frames 11500...
36355
+ [2024-11-08 07:30:41,466][41694] Num frames 11600...
36356
+ [2024-11-08 07:30:41,907][41694] Num frames 11700...
36357
+ [2024-11-08 07:30:42,105][41694] Avg episode rewards: #0: 4.705, true rewards: #0: 4.050
36358
+ [2024-11-08 07:30:42,107][41694] Avg episode reward: 4.705, avg true_objective: 4.050
36359
+ [2024-11-08 07:30:42,384][41694] Num frames 11800...
36360
+ [2024-11-08 07:30:42,930][41694] Num frames 11900...
36361
+ [2024-11-08 07:30:43,457][41694] Num frames 12000...
36362
+ [2024-11-08 07:30:43,919][41694] Num frames 12100...
36363
+ [2024-11-08 07:30:44,544][41694] Avg episode rewards: #0: 4.731, true rewards: #0: 4.064
36364
+ [2024-11-08 07:30:44,546][41694] Avg episode reward: 4.731, avg true_objective: 4.064
36365
+ [2024-11-08 07:30:44,604][41694] Num frames 12200...
36366
+ [2024-11-08 07:30:45,005][41694] Num frames 12300...
36367
+ [2024-11-08 07:30:45,511][41694] Num frames 12400...
36368
+ [2024-11-08 07:30:45,947][41694] Num frames 12500...
36369
+ [2024-11-08 07:30:46,308][41694] Num frames 12600...
36370
+ [2024-11-08 07:30:46,392][41694] Avg episode rewards: #0: 4.745, true rewards: #0: 4.067
36371
+ [2024-11-08 07:30:46,394][41694] Avg episode reward: 4.745, avg true_objective: 4.067
36372
+ [2024-11-08 07:30:46,604][41694] Num frames 12700...
36373
+ [2024-11-08 07:30:46,828][41694] Num frames 12800...
36374
+ [2024-11-08 07:30:47,103][41694] Num frames 12900...
36375
+ [2024-11-08 07:30:47,405][41694] Num frames 13000...
36376
+ [2024-11-08 07:30:47,580][41694] Avg episode rewards: #0: 4.768, true rewards: #0: 4.080
36377
+ [2024-11-08 07:30:47,584][41694] Avg episode reward: 4.768, avg true_objective: 4.080
36378
+ [2024-11-08 07:30:47,677][41694] Num frames 13100...
36379
+ [2024-11-08 07:30:47,888][41694] Num frames 13200...
36380
+ [2024-11-08 07:30:48,098][41694] Num frames 13300...
36381
+ [2024-11-08 07:30:48,318][41694] Num frames 13400...
36382
+ [2024-11-08 07:30:48,545][41694] Num frames 13500...
36383
+ [2024-11-08 07:30:48,609][41694] Avg episode rewards: #0: 4.789, true rewards: #0: 4.092
36384
+ [2024-11-08 07:30:48,612][41694] Avg episode reward: 4.789, avg true_objective: 4.092
36385
+ [2024-11-08 07:30:48,934][41694] Num frames 13600...
36386
+ [2024-11-08 07:30:49,193][41694] Num frames 13700...
36387
+ [2024-11-08 07:30:49,384][41694] Num frames 13800...
36388
+ [2024-11-08 07:30:49,612][41694] Avg episode rewards: #0: 4.761, true rewards: #0: 4.085
36389
+ [2024-11-08 07:30:49,614][41694] Avg episode reward: 4.761, avg true_objective: 4.085
36390
+ [2024-11-08 07:30:49,645][41694] Num frames 13900...
36391
+ [2024-11-08 07:30:49,863][41694] Num frames 14000...
36392
+ [2024-11-08 07:30:50,080][41694] Num frames 14100...
36393
+ [2024-11-08 07:30:50,508][41694] Num frames 14200...
36394
+ [2024-11-08 07:30:50,765][41694] Num frames 14300...
36395
+ [2024-11-08 07:30:50,830][41694] Avg episode rewards: #0: 4.773, true rewards: #0: 4.087
36396
+ [2024-11-08 07:30:50,833][41694] Avg episode reward: 4.773, avg true_objective: 4.087
36397
+ [2024-11-08 07:30:51,033][41694] Num frames 14400...
36398
+ [2024-11-08 07:30:51,250][41694] Num frames 14500...
36399
+ [2024-11-08 07:30:51,467][41694] Num frames 14600...
36400
+ [2024-11-08 07:30:51,692][41694] Avg episode rewards: #0: 4.747, true rewards: #0: 4.080
36401
+ [2024-11-08 07:30:51,695][41694] Avg episode reward: 4.747, avg true_objective: 4.080
36402
+ [2024-11-08 07:30:51,743][41694] Num frames 14700...
36403
+ [2024-11-08 07:30:52,171][41694] Num frames 14800...
36404
+ [2024-11-08 07:30:52,586][41694] Num frames 14900...
36405
+ [2024-11-08 07:30:52,976][41694] Num frames 15000...
36406
+ [2024-11-08 07:30:53,293][41694] Avg episode rewards: #0: 4.722, true rewards: #0: 4.074
36407
+ [2024-11-08 07:30:53,294][41694] Avg episode reward: 4.722, avg true_objective: 4.074
36408
+ [2024-11-08 07:30:53,355][41694] Num frames 15100...
36409
+ [2024-11-08 07:30:53,598][41694] Num frames 15200...
36410
+ [2024-11-08 07:30:53,870][41694] Num frames 15300...
36411
+ [2024-11-08 07:30:54,084][41694] Num frames 15400...
36412
+ [2024-11-08 07:30:54,319][41694] Avg episode rewards: #0: 4.734, true rewards: #0: 4.076
36413
+ [2024-11-08 07:30:54,321][41694] Avg episode reward: 4.734, avg true_objective: 4.076
36414
+ [2024-11-08 07:30:54,358][41694] Num frames 15500...
36415
+ [2024-11-08 07:30:54,578][41694] Num frames 15600...
36416
+ [2024-11-08 07:30:54,845][41694] Num frames 15700...
36417
+ [2024-11-08 07:30:55,168][41694] Num frames 15800...
36418
+ [2024-11-08 07:30:55,542][41694] Num frames 15900...
36419
+ [2024-11-08 07:30:55,724][41694] Avg episode rewards: #0: 4.753, true rewards: #0: 4.086
36420
+ [2024-11-08 07:30:55,725][41694] Avg episode reward: 4.753, avg true_objective: 4.086
36421
+ [2024-11-08 07:30:55,941][41694] Num frames 16000...
36422
+ [2024-11-08 07:30:56,264][41694] Num frames 16100...
36423
+ [2024-11-08 07:30:56,530][41694] Num frames 16200...
36424
+ [2024-11-08 07:30:56,859][41694] Num frames 16300...
36425
+ [2024-11-08 07:30:56,974][41694] Avg episode rewards: #0: 4.730, true rewards: #0: 4.080
36426
+ [2024-11-08 07:30:56,976][41694] Avg episode reward: 4.730, avg true_objective: 4.080
36427
+ [2024-11-08 07:30:57,333][41694] Num frames 16400...
36428
+ [2024-11-08 07:30:57,733][41694] Num frames 16500...
36429
+ [2024-11-08 07:30:57,996][41694] Num frames 16600...
36430
+ [2024-11-08 07:30:58,229][41694] Num frames 16700...
36431
+ [2024-11-08 07:30:58,539][41694] Num frames 16800...
36432
+ [2024-11-08 07:30:58,592][41694] Avg episode rewards: #0: 4.756, true rewards: #0: 4.098
36433
+ [2024-11-08 07:30:58,594][41694] Avg episode reward: 4.756, avg true_objective: 4.098
36434
+ [2024-11-08 07:30:58,848][41694] Num frames 16900...
36435
+ [2024-11-08 07:30:59,225][41694] Num frames 17000...
36436
+ [2024-11-08 07:30:59,502][41694] Num frames 17100...
36437
+ [2024-11-08 07:30:59,737][41694] Num frames 17200...
36438
+ [2024-11-08 07:30:59,901][41694] Avg episode rewards: #0: 4.773, true rewards: #0: 4.107
36439
+ [2024-11-08 07:30:59,903][41694] Avg episode reward: 4.773, avg true_objective: 4.107
36440
+ [2024-11-08 07:31:00,040][41694] Num frames 17300...
36441
+ [2024-11-08 07:31:00,295][41694] Num frames 17400...
36442
+ [2024-11-08 07:31:00,544][41694] Num frames 17500...
36443
+ [2024-11-08 07:31:00,977][41694] Num frames 17600...
36444
+ [2024-11-08 07:31:01,451][41694] Avg episode rewards: #0: 4.782, true rewards: #0: 4.108
36445
+ [2024-11-08 07:31:01,454][41694] Avg episode reward: 4.782, avg true_objective: 4.108
36446
+ [2024-11-08 07:31:01,558][41694] Num frames 17700...
36447
+ [2024-11-08 07:31:01,957][41694] Num frames 17800...
36448
+ [2024-11-08 07:31:02,399][41694] Num frames 17900...
36449
+ [2024-11-08 07:31:02,662][41694] Num frames 18000...
36450
+ [2024-11-08 07:31:02,848][41694] Avg episode rewards: #0: 4.761, true rewards: #0: 4.102
36451
+ [2024-11-08 07:31:02,850][41694] Avg episode reward: 4.761, avg true_objective: 4.102
36452
+ [2024-11-08 07:31:03,002][41694] Num frames 18100...
36453
+ [2024-11-08 07:31:03,283][41694] Num frames 18200...
36454
+ [2024-11-08 07:31:03,597][41694] Num frames 18300...
36455
+ [2024-11-08 07:31:04,027][41694] Num frames 18400...
36456
+ [2024-11-08 07:31:04,209][41694] Avg episode rewards: #0: 4.740, true rewards: #0: 4.096
36457
+ [2024-11-08 07:31:04,212][41694] Avg episode reward: 4.740, avg true_objective: 4.096
36458
+ [2024-11-08 07:31:04,536][41694] Num frames 18500...
36459
+ [2024-11-08 07:31:05,018][41694] Num frames 18600...
36460
+ [2024-11-08 07:31:05,437][41694] Num frames 18700...
36461
+ [2024-11-08 07:31:05,721][41694] Num frames 18800...
36462
+ [2024-11-08 07:31:06,002][41694] Num frames 18900...
36463
+ [2024-11-08 07:31:06,188][41694] Avg episode rewards: #0: 4.792, true rewards: #0: 4.118
36464
+ [2024-11-08 07:31:06,196][41694] Avg episode reward: 4.792, avg true_objective: 4.118
36465
+ [2024-11-08 07:31:06,339][41694] Num frames 19000...
36466
+ [2024-11-08 07:31:06,580][41694] Num frames 19100...
36467
+ [2024-11-08 07:31:06,798][41694] Num frames 19200...
36468
+ [2024-11-08 07:31:07,053][41694] Num frames 19300...
36469
+ [2024-11-08 07:31:07,191][41694] Avg episode rewards: #0: 4.772, true rewards: #0: 4.112
36470
+ [2024-11-08 07:31:07,194][41694] Avg episode reward: 4.772, avg true_objective: 4.112
36471
+ [2024-11-08 07:31:07,414][41694] Num frames 19400...
36472
+ [2024-11-08 07:31:07,853][41694] Num frames 19500...
36473
+ [2024-11-08 07:31:08,085][41694] Num frames 19600...
36474
+ [2024-11-08 07:31:08,249][41694] Avg episode rewards: #0: 4.760, true rewards: #0: 4.093
36475
+ [2024-11-08 07:31:08,253][41694] Avg episode reward: 4.760, avg true_objective: 4.093
36476
+ [2024-11-08 07:31:08,394][41694] Num frames 19700...
36477
+ [2024-11-08 07:31:08,612][41694] Num frames 19800...
36478
+ [2024-11-08 07:31:08,804][41694] Num frames 19900...
36479
+ [2024-11-08 07:31:09,021][41694] Num frames 20000...
36480
+ [2024-11-08 07:31:09,262][41694] Avg episode rewards: #0: 4.775, true rewards: #0: 4.101
36481
+ [2024-11-08 07:31:09,266][41694] Avg episode reward: 4.775, avg true_objective: 4.101
36482
+ [2024-11-08 07:31:09,293][41694] Num frames 20100...
36483
+ [2024-11-08 07:31:09,534][41694] Num frames 20200...
36484
+ [2024-11-08 07:31:09,745][41694] Num frames 20300...
36485
+ [2024-11-08 07:31:10,046][41694] Num frames 20400...
36486
+ [2024-11-08 07:31:10,293][41694] Avg episode rewards: #0: 4.756, true rewards: #0: 4.096
36487
+ [2024-11-08 07:31:10,294][41694] Avg episode reward: 4.756, avg true_objective: 4.096
36488
+ [2024-11-08 07:31:10,341][41694] Num frames 20500...
36489
+ [2024-11-08 07:31:10,564][41694] Num frames 20600...
36490
+ [2024-11-08 07:31:10,797][41694] Num frames 20700...
36491
+ [2024-11-08 07:31:11,041][41694] Num frames 20800...
36492
+ [2024-11-08 07:31:11,256][41694] Avg episode rewards: #0: 4.738, true rewards: #0: 4.091
36493
+ [2024-11-08 07:31:11,259][41694] Avg episode reward: 4.738, avg true_objective: 4.091
36494
+ [2024-11-08 07:31:11,339][41694] Num frames 20900...
36495
+ [2024-11-08 07:31:11,603][41694] Num frames 21000...
36496
+ [2024-11-08 07:31:11,868][41694] Num frames 21100...
36497
+ [2024-11-08 07:31:12,104][41694] Num frames 21200...
36498
+ [2024-11-08 07:31:12,345][41694] Avg episode rewards: #0: 4.746, true rewards: #0: 4.092
36499
+ [2024-11-08 07:31:12,346][41694] Avg episode reward: 4.746, avg true_objective: 4.092
36500
+ [2024-11-08 07:31:12,404][41694] Num frames 21300...
36501
+ [2024-11-08 07:31:12,655][41694] Num frames 21400...
36502
+ [2024-11-08 07:31:12,935][41694] Num frames 21500...
36503
+ [2024-11-08 07:31:13,099][41694] Avg episode rewards: #0: 4.705, true rewards: #0: 4.063
36504
+ [2024-11-08 07:31:13,101][41694] Avg episode reward: 4.705, avg true_objective: 4.063
36505
+ [2024-11-08 07:31:13,281][41694] Num frames 21600...
36506
+ [2024-11-08 07:31:13,584][41694] Num frames 21700...
36507
+ [2024-11-08 07:31:13,841][41694] Num frames 21800...
36508
+ [2024-11-08 07:31:14,056][41694] Num frames 21900...
36509
+ [2024-11-08 07:31:14,280][41694] Avg episode rewards: #0: 4.719, true rewards: #0: 4.071
36510
+ [2024-11-08 07:31:14,283][41694] Avg episode reward: 4.719, avg true_objective: 4.071
36511
+ [2024-11-08 07:31:14,340][41694] Num frames 22000...
36512
+ [2024-11-08 07:31:14,555][41694] Num frames 22100...
36513
+ [2024-11-08 07:31:14,769][41694] Num frames 22200...
36514
+ [2024-11-08 07:31:15,012][41694] Num frames 22300...
36515
+ [2024-11-08 07:31:15,256][41694] Avg episode rewards: #0: 4.703, true rewards: #0: 4.067
36516
+ [2024-11-08 07:31:15,258][41694] Avg episode reward: 4.703, avg true_objective: 4.067
36517
+ [2024-11-08 07:31:15,367][41694] Num frames 22400...
36518
+ [2024-11-08 07:31:15,630][41694] Num frames 22500...
36519
+ [2024-11-08 07:31:15,822][41694] Num frames 22600...
36520
+ [2024-11-08 07:31:16,108][41694] Num frames 22700...
36521
+ [2024-11-08 07:31:16,290][41694] Avg episode rewards: #0: 4.688, true rewards: #0: 4.063
36522
+ [2024-11-08 07:31:16,295][41694] Avg episode reward: 4.688, avg true_objective: 4.063
36523
+ [2024-11-08 07:31:16,408][41694] Num frames 22800...
36524
+ [2024-11-08 07:31:16,606][41694] Num frames 22900...
36525
+ [2024-11-08 07:31:16,824][41694] Num frames 23000...
36526
+ [2024-11-08 07:31:17,165][41694] Num frames 23100...
36527
+ [2024-11-08 07:31:17,310][41694] Avg episode rewards: #0: 4.673, true rewards: #0: 4.059
36528
+ [2024-11-08 07:31:17,315][41694] Avg episode reward: 4.673, avg true_objective: 4.059
36529
+ [2024-11-08 07:31:17,476][41694] Num frames 23200...
36530
+ [2024-11-08 07:31:17,720][41694] Num frames 23300...
36531
+ [2024-11-08 07:31:18,125][41694] Num frames 23400...
36532
+ [2024-11-08 07:31:18,474][41694] Num frames 23500...
36533
+ [2024-11-08 07:31:18,769][41694] Avg episode rewards: #0: 4.687, true rewards: #0: 4.066
36534
+ [2024-11-08 07:31:18,772][41694] Avg episode reward: 4.687, avg true_objective: 4.066
36535
+ [2024-11-08 07:31:18,873][41694] Num frames 23600...
36536
+ [2024-11-08 07:31:19,292][41694] Num frames 23700...
36537
+ [2024-11-08 07:31:19,537][41694] Num frames 23800...
36538
+ [2024-11-08 07:31:19,765][41694] Num frames 23900...
36539
+ [2024-11-08 07:31:20,057][41694] Num frames 24000...
36540
+ [2024-11-08 07:31:20,204][41694] Avg episode rewards: #0: 4.700, true rewards: #0: 4.073
36541
+ [2024-11-08 07:31:20,206][41694] Avg episode reward: 4.700, avg true_objective: 4.073
36542
+ [2024-11-08 07:31:20,445][41694] Num frames 24100...
36543
+ [2024-11-08 07:31:20,787][41694] Num frames 24200...
36544
+ [2024-11-08 07:31:21,033][41694] Num frames 24300...
36545
+ [2024-11-08 07:31:21,235][41694] Num frames 24400...
36546
+ [2024-11-08 07:31:21,331][41694] Avg episode rewards: #0: 4.686, true rewards: #0: 4.069
36547
+ [2024-11-08 07:31:21,337][41694] Avg episode reward: 4.686, avg true_objective: 4.069
36548
+ [2024-11-08 07:31:21,530][41694] Num frames 24500...
36549
+ [2024-11-08 07:31:21,801][41694] Num frames 24600...
36550
+ [2024-11-08 07:31:22,067][41694] Num frames 24700...
36551
+ [2024-11-08 07:31:22,314][41694] Num frames 24800...
36552
+ [2024-11-08 07:31:22,368][41694] Avg episode rewards: #0: 4.672, true rewards: #0: 4.066
36553
+ [2024-11-08 07:31:22,370][41694] Avg episode reward: 4.672, avg true_objective: 4.066
36554
+ [2024-11-08 07:31:22,655][41694] Num frames 24900...
36555
+ [2024-11-08 07:31:22,855][41694] Num frames 25000...
36556
+ [2024-11-08 07:31:23,061][41694] Num frames 25100...
36557
+ [2024-11-08 07:31:23,285][41694] Avg episode rewards: #0: 4.659, true rewards: #0: 4.062
36558
+ [2024-11-08 07:31:23,288][41694] Avg episode reward: 4.659, avg true_objective: 4.062
36559
+ [2024-11-08 07:31:23,340][41694] Num frames 25200...
36560
+ [2024-11-08 07:31:23,610][41694] Num frames 25300...
36561
+ [2024-11-08 07:31:23,966][41694] Num frames 25400...
36562
+ [2024-11-08 07:31:24,123][41694] Avg episode rewards: #0: 4.625, true rewards: #0: 4.038
36563
+ [2024-11-08 07:31:24,127][41694] Avg episode reward: 4.625, avg true_objective: 4.038
36564
+ [2024-11-08 07:31:24,267][41694] Num frames 25500...
36565
+ [2024-11-08 07:31:24,524][41694] Num frames 25600...
36566
+ [2024-11-08 07:31:24,841][41694] Num frames 25700...
36567
+ [2024-11-08 07:31:25,074][41694] Num frames 25800...
36568
+ [2024-11-08 07:31:25,188][41694] Avg episode rewards: #0: 4.613, true rewards: #0: 4.035
36569
+ [2024-11-08 07:31:25,189][41694] Avg episode reward: 4.613, avg true_objective: 4.035
36570
+ [2024-11-08 07:31:25,366][41694] Num frames 25900...
36571
+ [2024-11-08 07:31:25,582][41694] Num frames 26000...
36572
+ [2024-11-08 07:31:25,816][41694] Num frames 26100...
36573
+ [2024-11-08 07:31:26,135][41694] Num frames 26200...
36574
+ [2024-11-08 07:31:26,236][41694] Avg episode rewards: #0: 4.601, true rewards: #0: 4.032
36575
+ [2024-11-08 07:31:26,239][41694] Avg episode reward: 4.601, avg true_objective: 4.032
36576
+ [2024-11-08 07:31:26,573][41694] Num frames 26300...
36577
+ [2024-11-08 07:31:26,892][41694] Num frames 26400...
36578
+ [2024-11-08 07:31:27,357][41694] Num frames 26500...
36579
+ [2024-11-08 07:31:27,851][41694] Avg episode rewards: #0: 4.590, true rewards: #0: 4.029
36580
+ [2024-11-08 07:31:27,854][41694] Avg episode reward: 4.590, avg true_objective: 4.029
36581
+ [2024-11-08 07:31:27,884][41694] Num frames 26600...
36582
+ [2024-11-08 07:31:28,188][41694] Num frames 26700...
36583
+ [2024-11-08 07:31:28,592][41694] Num frames 26800...
36584
+ [2024-11-08 07:31:28,886][41694] Num frames 26900...
36585
+ [2024-11-08 07:31:29,147][41694] Num frames 27000...
36586
+ [2024-11-08 07:31:29,296][41694] Avg episode rewards: #0: 4.603, true rewards: #0: 4.036
36587
+ [2024-11-08 07:31:29,299][41694] Avg episode reward: 4.603, avg true_objective: 4.036
36588
+ [2024-11-08 07:31:29,493][41694] Num frames 27100...
36589
+ [2024-11-08 07:31:29,788][41694] Num frames 27200...
36590
+ [2024-11-08 07:31:30,071][41694] Num frames 27300...
36591
+ [2024-11-08 07:31:30,483][41694] Num frames 27400...
36592
+ [2024-11-08 07:31:30,833][41694] Avg episode rewards: #0: 4.616, true rewards: #0: 4.042
36593
+ [2024-11-08 07:31:30,837][41694] Avg episode reward: 4.616, avg true_objective: 4.042
36594
+ [2024-11-08 07:31:30,910][41694] Num frames 27500...
36595
+ [2024-11-08 07:31:31,153][41694] Num frames 27600...
36596
+ [2024-11-08 07:31:31,369][41694] Num frames 27700...
36597
+ [2024-11-08 07:31:31,583][41694] Num frames 27800...
36598
+ [2024-11-08 07:31:31,795][41694] Num frames 27900...
36599
+ [2024-11-08 07:31:31,989][41694] Num frames 28000...
36600
+ [2024-11-08 07:31:32,117][41694] Avg episode rewards: #0: 4.657, true rewards: #0: 4.063
36601
+ [2024-11-08 07:31:32,121][41694] Avg episode reward: 4.657, avg true_objective: 4.063
36602
+ [2024-11-08 07:31:32,279][41694] Num frames 28100...
36603
+ [2024-11-08 07:31:32,483][41694] Num frames 28200...
36604
+ [2024-11-08 07:31:32,818][41694] Num frames 28300...
36605
+ [2024-11-08 07:31:33,079][41694] Num frames 28400...
36606
+ [2024-11-08 07:31:33,186][41694] Avg episode rewards: #0: 4.645, true rewards: #0: 4.059
36607
+ [2024-11-08 07:31:33,190][41694] Avg episode reward: 4.645, avg true_objective: 4.059
36608
+ [2024-11-08 07:31:33,404][41694] Num frames 28500...
36609
+ [2024-11-08 07:31:33,635][41694] Num frames 28600...
36610
+ [2024-11-08 07:31:33,957][41694] Num frames 28700...
36611
+ [2024-11-08 07:31:34,229][41694] Num frames 28800...
36612
+ [2024-11-08 07:31:34,282][41694] Avg episode rewards: #0: 4.634, true rewards: #0: 4.056
36613
+ [2024-11-08 07:31:34,284][41694] Avg episode reward: 4.634, avg true_objective: 4.056
36614
+ [2024-11-08 07:31:34,797][41694] Num frames 28900...
36615
+ [2024-11-08 07:31:35,487][41694] Num frames 29000...
36616
+ [2024-11-08 07:31:36,167][41694] Num frames 29100...
36617
+ [2024-11-08 07:31:36,718][41694] Num frames 29200...
36618
+ [2024-11-08 07:31:36,927][41694] Avg episode rewards: #0: 4.646, true rewards: #0: 4.062
36619
+ [2024-11-08 07:31:36,930][41694] Avg episode reward: 4.646, avg true_objective: 4.062
36620
+ [2024-11-08 07:31:37,113][41694] Num frames 29300...
36621
+ [2024-11-08 07:31:37,661][41694] Num frames 29400...
36622
+ [2024-11-08 07:31:38,407][41694] Num frames 29500...
36623
+ [2024-11-08 07:31:38,949][41694] Num frames 29600...
36624
+ [2024-11-08 07:31:39,500][41694] Num frames 29700...
36625
+ [2024-11-08 07:31:40,096][41694] Avg episode rewards: #0: 4.684, true rewards: #0: 4.081
36626
+ [2024-11-08 07:31:40,098][41694] Avg episode reward: 4.684, avg true_objective: 4.081
36627
+ [2024-11-08 07:31:40,150][41694] Num frames 29800...
36628
+ [2024-11-08 07:31:40,741][41694] Num frames 29900...
36629
+ [2024-11-08 07:31:41,206][41694] Num frames 30000...
36630
+ [2024-11-08 07:31:41,701][41694] Num frames 30100...
36631
+ [2024-11-08 07:31:42,314][41694] Avg episode rewards: #0: 4.672, true rewards: #0: 4.078
36632
+ [2024-11-08 07:31:42,319][41694] Avg episode reward: 4.672, avg true_objective: 4.078
36633
+ [2024-11-08 07:31:42,556][41694] Num frames 30200...
36634
+ [2024-11-08 07:31:43,282][41694] Num frames 30300...
36635
+ [2024-11-08 07:31:43,784][41694] Num frames 30400...
36636
+ [2024-11-08 07:31:44,202][41694] Num frames 30500...
36637
+ [2024-11-08 07:31:44,421][41694] Avg episode rewards: #0: 4.661, true rewards: #0: 4.075
36638
+ [2024-11-08 07:31:44,424][41694] Avg episode reward: 4.661, avg true_objective: 4.075
36639
+ [2024-11-08 07:31:44,561][41694] Num frames 30600...
36640
+ [2024-11-08 07:31:44,926][41694] Num frames 30700...
36641
+ [2024-11-08 07:31:45,279][41694] Num frames 30800...
36642
+ [2024-11-08 07:31:45,677][41694] Num frames 30900...
36643
+ [2024-11-08 07:31:45,861][41694] Avg episode rewards: #0: 4.651, true rewards: #0: 4.072
36644
+ [2024-11-08 07:31:45,862][41694] Avg episode reward: 4.651, avg true_objective: 4.072
36645
+ [2024-11-08 07:31:46,053][41694] Num frames 31000...
36646
+ [2024-11-08 07:31:46,375][41694] Num frames 31100...
36647
+ [2024-11-08 07:31:46,652][41694] Num frames 31200...
36648
+ [2024-11-08 07:31:47,104][41694] Num frames 31300...
36649
+ [2024-11-08 07:31:47,329][41694] Avg episode rewards: #0: 4.640, true rewards: #0: 4.069
36650
+ [2024-11-08 07:31:47,332][41694] Avg episode reward: 4.640, avg true_objective: 4.069
36651
+ [2024-11-08 07:31:47,638][41694] Num frames 31400...
36652
+ [2024-11-08 07:31:48,021][41694] Num frames 31500...
36653
+ [2024-11-08 07:31:48,466][41694] Num frames 31600...
36654
+ [2024-11-08 07:31:48,988][41694] Num frames 31700...
36655
+ [2024-11-08 07:31:49,097][41694] Avg episode rewards: #0: 4.630, true rewards: #0: 4.066
36656
+ [2024-11-08 07:31:49,101][41694] Avg episode reward: 4.630, avg true_objective: 4.066
36657
+ [2024-11-08 07:31:49,497][41694] Num frames 31800...
36658
+ [2024-11-08 07:31:49,791][41694] Num frames 31900...
36659
+ [2024-11-08 07:31:50,331][41694] Num frames 32000...
36660
+ [2024-11-08 07:31:50,654][41694] Avg episode rewards: #0: 4.620, true rewards: #0: 4.063
36661
+ [2024-11-08 07:31:50,655][41694] Avg episode reward: 4.620, avg true_objective: 4.063
36662
+ [2024-11-08 07:31:50,667][41694] Num frames 32100...
36663
+ [2024-11-08 07:31:51,086][41694] Num frames 32200...
36664
+ [2024-11-08 07:31:51,454][41694] Num frames 32300...
36665
+ [2024-11-08 07:31:51,923][41694] Num frames 32400...
36666
+ [2024-11-08 07:31:52,392][41694] Num frames 32500...
36667
+ [2024-11-08 07:31:52,716][41694] Avg episode rewards: #0: 4.631, true rewards: #0: 4.068
36668
+ [2024-11-08 07:31:52,719][41694] Avg episode reward: 4.631, avg true_objective: 4.068
36669
+ [2024-11-08 07:31:52,931][41694] Num frames 32600...
36670
+ [2024-11-08 07:31:53,310][41694] Num frames 32700...
36671
+ [2024-11-08 07:31:53,780][41694] Num frames 32800...
36672
+ [2024-11-08 07:31:54,199][41694] Num frames 32900...
36673
+ [2024-11-08 07:31:54,340][41694] Avg episode rewards: #0: 4.621, true rewards: #0: 4.065
36674
+ [2024-11-08 07:31:54,342][41694] Avg episode reward: 4.621, avg true_objective: 4.065
36675
+ [2024-11-08 07:31:54,548][41694] Num frames 33000...
36676
+ [2024-11-08 07:31:54,898][41694] Num frames 33100...
36677
+ [2024-11-08 07:31:55,203][41694] Num frames 33200...
36678
+ [2024-11-08 07:31:55,497][41694] Num frames 33300...
36679
+ [2024-11-08 07:31:55,782][41694] Avg episode rewards: #0: 4.631, true rewards: #0: 4.070
36680
+ [2024-11-08 07:31:55,786][41694] Avg episode reward: 4.631, avg true_objective: 4.070
36681
+ [2024-11-08 07:31:55,864][41694] Num frames 33400...
36682
+ [2024-11-08 07:31:56,132][41694] Num frames 33500...
36683
+ [2024-11-08 07:31:56,397][41694] Num frames 33600...
36684
+ [2024-11-08 07:31:56,673][41694] Num frames 33700...
36685
+ [2024-11-08 07:31:56,951][41694] Avg episode rewards: #0: 4.622, true rewards: #0: 4.067
36686
+ [2024-11-08 07:31:56,953][41694] Avg episode reward: 4.622, avg true_objective: 4.067
36687
+ [2024-11-08 07:31:57,051][41694] Num frames 33800...
36688
+ [2024-11-08 07:31:57,262][41694] Num frames 33900...
36689
+ [2024-11-08 07:31:57,466][41694] Num frames 34000...
36690
+ [2024-11-08 07:31:57,663][41694] Num frames 34100...
36691
+ [2024-11-08 07:31:57,725][41694] Avg episode rewards: #0: 4.607, true rewards: #0: 4.060
36692
+ [2024-11-08 07:31:57,730][41694] Avg episode reward: 4.607, avg true_objective: 4.060
36693
+ [2024-11-08 07:31:57,954][41694] Num frames 34200...
36694
+ [2024-11-08 07:31:58,156][41694] Num frames 34300...
36695
+ [2024-11-08 07:31:58,346][41694] Num frames 34400...
36696
+ [2024-11-08 07:31:58,545][41694] Num frames 34500...
36697
+ [2024-11-08 07:31:58,638][41694] Avg episode rewards: #0: 4.614, true rewards: #0: 4.061
36698
+ [2024-11-08 07:31:58,641][41694] Avg episode reward: 4.614, avg true_objective: 4.061
36699
+ [2024-11-08 07:31:58,831][41694] Num frames 34600...
36700
+ [2024-11-08 07:31:59,020][41694] Num frames 34700...
36701
+ [2024-11-08 07:31:59,225][41694] Num frames 34800...
36702
+ [2024-11-08 07:31:59,430][41694] Num frames 34900...
36703
+ [2024-11-08 07:31:59,555][41694] Avg episode rewards: #0: 4.620, true rewards: #0: 4.062
36704
+ [2024-11-08 07:31:59,562][41694] Avg episode reward: 4.620, avg true_objective: 4.062
36705
+ [2024-11-08 07:31:59,696][41694] Num frames 35000...
36706
+ [2024-11-08 07:31:59,888][41694] Num frames 35100...
36707
+ [2024-11-08 07:32:00,098][41694] Num frames 35200...
36708
+ [2024-11-08 07:32:00,327][41694] Num frames 35300...
36709
+ [2024-11-08 07:32:00,427][41694] Avg episode rewards: #0: 4.611, true rewards: #0: 4.059
36710
+ [2024-11-08 07:32:00,430][41694] Avg episode reward: 4.611, avg true_objective: 4.059
36711
+ [2024-11-08 07:32:00,670][41694] Num frames 35400...
36712
+ [2024-11-08 07:32:00,974][41694] Num frames 35500...
36713
+ [2024-11-08 07:32:01,256][41694] Num frames 35600...
36714
+ [2024-11-08 07:32:01,555][41694] Num frames 35700...
36715
+ [2024-11-08 07:32:01,619][41694] Avg episode rewards: #0: 4.602, true rewards: #0: 4.057
36716
+ [2024-11-08 07:32:01,622][41694] Avg episode reward: 4.602, avg true_objective: 4.057
36717
+ [2024-11-08 07:32:01,841][41694] Num frames 35800...
36718
+ [2024-11-08 07:32:02,034][41694] Num frames 35900...
36719
+ [2024-11-08 07:32:02,231][41694] Num frames 36000...
36720
+ [2024-11-08 07:32:02,438][41694] Avg episode rewards: #0: 4.601, true rewards: #0: 4.051
36721
+ [2024-11-08 07:32:02,441][41694] Avg episode reward: 4.601, avg true_objective: 4.051
36722
+ [2024-11-08 07:32:02,549][41694] Num frames 36100...
36723
+ [2024-11-08 07:32:02,834][41694] Num frames 36200...
36724
+ [2024-11-08 07:32:03,202][41694] Num frames 36300...
36725
+ [2024-11-08 07:32:03,426][41694] Num frames 36400...
36726
+ [2024-11-08 07:32:03,646][41694] Avg episode rewards: #0: 4.597, true rewards: #0: 4.052
36727
+ [2024-11-08 07:32:03,650][41694] Avg episode reward: 4.597, avg true_objective: 4.052
36728
+ [2024-11-08 07:32:03,727][41694] Num frames 36500...
36729
+ [2024-11-08 07:32:03,941][41694] Num frames 36600...
36730
+ [2024-11-08 07:32:04,258][41694] Num frames 36700...
36731
+ [2024-11-08 07:32:04,471][41694] Num frames 36800...
36732
+ [2024-11-08 07:32:04,776][41694] Num frames 36900...
36733
+ [2024-11-08 07:32:04,877][41694] Avg episode rewards: #0: 4.606, true rewards: #0: 4.057
36734
+ [2024-11-08 07:32:04,881][41694] Avg episode reward: 4.606, avg true_objective: 4.057
36735
+ [2024-11-08 07:32:05,069][41694] Num frames 37000...
36736
+ [2024-11-08 07:32:05,281][41694] Num frames 37100...
36737
+ [2024-11-08 07:32:05,503][41694] Num frames 37200...
36738
+ [2024-11-08 07:32:05,787][41694] Num frames 37300...
36739
+ [2024-11-08 07:32:05,990][41694] Avg episode rewards: #0: 4.612, true rewards: #0: 4.058
36740
+ [2024-11-08 07:32:05,994][41694] Avg episode reward: 4.612, avg true_objective: 4.058
36741
+ [2024-11-08 07:32:06,179][41694] Num frames 37400...
36742
+ [2024-11-08 07:32:06,448][41694] Num frames 37500...
36743
+ [2024-11-08 07:32:06,767][41694] Num frames 37600...
36744
+ [2024-11-08 07:32:07,060][41694] Num frames 37700...
36745
+ [2024-11-08 07:32:07,330][41694] Num frames 37800...
36746
+ [2024-11-08 07:32:07,603][41694] Avg episode rewards: #0: 4.643, true rewards: #0: 4.073
36747
+ [2024-11-08 07:32:07,605][41694] Avg episode reward: 4.643, avg true_objective: 4.073
36748
+ [2024-11-08 07:32:07,707][41694] Num frames 37900...
36749
+ [2024-11-08 07:32:08,006][41694] Num frames 38000...
36750
+ [2024-11-08 07:32:08,269][41694] Num frames 38100...
36751
+ [2024-11-08 07:32:08,637][41694] Num frames 38200...
36752
+ [2024-11-08 07:32:08,953][41694] Avg episode rewards: #0: 4.634, true rewards: #0: 4.070
36753
+ [2024-11-08 07:32:08,956][41694] Avg episode reward: 4.634, avg true_objective: 4.070
36754
+ [2024-11-08 07:32:09,061][41694] Num frames 38300...
36755
+ [2024-11-08 07:32:09,255][41694] Num frames 38400...
36756
+ [2024-11-08 07:32:09,459][41694] Num frames 38500...
36757
+ [2024-11-08 07:32:09,655][41694] Num frames 38600...
36758
+ [2024-11-08 07:32:09,865][41694] Num frames 38700...
36759
+ [2024-11-08 07:32:09,943][41694] Avg episode rewards: #0: 4.643, true rewards: #0: 4.075
36760
+ [2024-11-08 07:32:09,947][41694] Avg episode reward: 4.643, avg true_objective: 4.075
36761
+ [2024-11-08 07:32:10,138][41694] Num frames 38800...
36762
+ [2024-11-08 07:32:10,322][41694] Num frames 38900...
36763
+ [2024-11-08 07:32:10,514][41694] Num frames 39000...
36764
+ [2024-11-08 07:32:10,743][41694] Avg episode rewards: #0: 4.635, true rewards: #0: 4.072
36765
+ [2024-11-08 07:32:10,748][41694] Avg episode reward: 4.635, avg true_objective: 4.072
36766
+ [2024-11-08 07:32:10,783][41694] Num frames 39100...
36767
+ [2024-11-08 07:32:10,986][41694] Num frames 39200...
36768
+ [2024-11-08 07:32:11,181][41694] Num frames 39300...
36769
+ [2024-11-08 07:32:11,376][41694] Num frames 39400...
36770
+ [2024-11-08 07:32:11,582][41694] Avg episode rewards: #0: 4.627, true rewards: #0: 4.070
36771
+ [2024-11-08 07:32:11,585][41694] Avg episode reward: 4.627, avg true_objective: 4.070
36772
+ [2024-11-08 07:32:11,655][41694] Num frames 39500...
36773
+ [2024-11-08 07:32:11,850][41694] Num frames 39600...
36774
+ [2024-11-08 07:32:12,052][41694] Num frames 39700...
36775
+ [2024-11-08 07:32:12,244][41694] Num frames 39800...
36776
+ [2024-11-08 07:32:12,416][41694] Avg episode rewards: #0: 4.618, true rewards: #0: 4.067
36777
+ [2024-11-08 07:32:12,419][41694] Avg episode reward: 4.618, avg true_objective: 4.067
36778
+ [2024-11-08 07:32:12,519][41694] Num frames 39900...
36779
+ [2024-11-08 07:32:12,725][41694] Num frames 40000...
36780
+ [2024-11-08 07:32:12,923][41694] Num frames 40100...
36781
+ [2024-11-08 07:32:13,122][41694] Num frames 40200...
36782
+ [2024-11-08 07:32:13,317][41694] Num frames 40300...
36783
+ [2024-11-08 07:32:13,394][41694] Avg episode rewards: #0: 4.627, true rewards: #0: 4.072
36784
+ [2024-11-08 07:32:13,398][41694] Avg episode reward: 4.627, avg true_objective: 4.072
36785
+ [2024-11-08 07:32:13,589][41694] Num frames 40400...
36786
+ [2024-11-08 07:32:13,790][41694] Num frames 40500...
36787
+ [2024-11-08 07:32:14,006][41694] Num frames 40600...
36788
+ [2024-11-08 07:32:14,337][41694] Avg episode rewards: #0: 4.619, true rewards: #0: 4.069
36789
+ [2024-11-08 07:32:14,339][41694] Avg episode reward: 4.619, avg true_objective: 4.069
36790
+ [2024-11-08 07:34:27,542][41694] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!