usamabuttar commited on
Commit
2637f1c
1 Parent(s): 88a2333

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 +389 -0
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 10.42 +/- 6.47
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 10.86 +/- 5.66
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 sha256:7b2aab48f43596258c5bf3e708e45d09a12ae62d8ffb438d9d56bcde6296976b
3
- size 19931035
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b67cd4da3c41e52b42a9406b2fcfda2584df97ee5e633a70e1adaf4bad6ab0
3
+ size 20837753
sf_log.txt CHANGED
@@ -1115,3 +1115,392 @@ main_loop: 1103.4782
1115
  [2024-11-11 14:41:28,081][00562] Avg episode rewards: #0: 23.522, true rewards: #0: 10.422
1116
  [2024-11-11 14:41:28,082][00562] Avg episode reward: 23.522, avg true_objective: 10.422
1117
  [2024-11-11 14:42:30,928][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1115
  [2024-11-11 14:41:28,081][00562] Avg episode rewards: #0: 23.522, true rewards: #0: 10.422
1116
  [2024-11-11 14:41:28,082][00562] Avg episode reward: 23.522, avg true_objective: 10.422
1117
  [2024-11-11 14:42:30,928][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
1118
+ [2024-11-11 14:42:38,969][00562] The model has been pushed to https://huggingface.co/usamabuttar/rl_course_vizdoom_health_gathering_supreme
1119
+ [2024-11-11 14:45:46,383][00562] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
1120
+ [2024-11-11 14:45:46,385][00562] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
1121
+ [2024-11-11 14:45:46,387][00562] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
1122
+ [2024-11-11 14:45:46,389][00562] Overriding arg 'train_dir' with value 'train_dir' passed from command line
1123
+ [2024-11-11 14:45:46,390][00562] Overriding arg 'num_workers' with value 1 passed from command line
1124
+ [2024-11-11 14:45:46,396][00562] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
1125
+ [2024-11-11 14:45:46,397][00562] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
1126
+ [2024-11-11 14:45:46,398][00562] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
1127
+ [2024-11-11 14:45:46,401][00562] Adding new argument 'no_render'=True that is not in the saved config file!
1128
+ [2024-11-11 14:45:46,402][00562] Adding new argument 'save_video'=True that is not in the saved config file!
1129
+ [2024-11-11 14:45:46,403][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1130
+ [2024-11-11 14:45:46,404][00562] Adding new argument 'video_name'=None that is not in the saved config file!
1131
+ [2024-11-11 14:45:46,405][00562] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
1132
+ [2024-11-11 14:45:46,407][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1133
+ [2024-11-11 14:45:46,408][00562] Adding new argument 'push_to_hub'=False that is not in the saved config file!
1134
+ [2024-11-11 14:45:46,409][00562] Adding new argument 'hf_repository'=None that is not in the saved config file!
1135
+ [2024-11-11 14:45:46,410][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
1136
+ [2024-11-11 14:45:46,410][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1137
+ [2024-11-11 14:45:46,411][00562] Adding new argument 'train_script'=None that is not in the saved config file!
1138
+ [2024-11-11 14:45:46,412][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1139
+ [2024-11-11 14:45:46,414][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
1140
+ [2024-11-11 14:45:46,458][00562] RunningMeanStd input shape: (3, 72, 128)
1141
+ [2024-11-11 14:45:46,460][00562] RunningMeanStd input shape: (1,)
1142
+ [2024-11-11 14:45:46,472][00562] ConvEncoder: input_channels=3
1143
+ [2024-11-11 14:45:46,522][00562] Conv encoder output size: 512
1144
+ [2024-11-11 14:45:46,524][00562] Policy head output size: 512
1145
+ [2024-11-11 14:45:46,546][00562] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
1146
+ [2024-11-11 14:45:46,964][00562] Num frames 100...
1147
+ [2024-11-11 14:45:47,093][00562] Num frames 200...
1148
+ [2024-11-11 14:45:47,243][00562] Num frames 300...
1149
+ [2024-11-11 14:45:47,373][00562] Num frames 400...
1150
+ [2024-11-11 14:45:47,505][00562] Num frames 500...
1151
+ [2024-11-11 14:45:47,627][00562] Num frames 600...
1152
+ [2024-11-11 14:45:47,752][00562] Num frames 700...
1153
+ [2024-11-11 14:45:47,877][00562] Num frames 800...
1154
+ [2024-11-11 14:45:48,011][00562] Num frames 900...
1155
+ [2024-11-11 14:45:48,141][00562] Num frames 1000...
1156
+ [2024-11-11 14:45:48,263][00562] Num frames 1100...
1157
+ [2024-11-11 14:45:48,387][00562] Num frames 1200...
1158
+ [2024-11-11 14:45:48,521][00562] Num frames 1300...
1159
+ [2024-11-11 14:45:48,640][00562] Num frames 1400...
1160
+ [2024-11-11 14:45:48,762][00562] Num frames 1500...
1161
+ [2024-11-11 14:45:48,886][00562] Num frames 1600...
1162
+ [2024-11-11 14:45:49,006][00562] Num frames 1700...
1163
+ [2024-11-11 14:45:49,132][00562] Num frames 1800...
1164
+ [2024-11-11 14:45:49,251][00562] Num frames 1900...
1165
+ [2024-11-11 14:45:49,381][00562] Num frames 2000...
1166
+ [2024-11-11 14:45:49,511][00562] Num frames 2100...
1167
+ [2024-11-11 14:45:49,564][00562] Avg episode rewards: #0: 65.998, true rewards: #0: 21.000
1168
+ [2024-11-11 14:45:49,567][00562] Avg episode reward: 65.998, avg true_objective: 21.000
1169
+ [2024-11-11 14:45:49,685][00562] Num frames 2200...
1170
+ [2024-11-11 14:45:49,804][00562] Num frames 2300...
1171
+ [2024-11-11 14:45:49,925][00562] Num frames 2400...
1172
+ [2024-11-11 14:45:50,044][00562] Num frames 2500...
1173
+ [2024-11-11 14:45:50,174][00562] Num frames 2600...
1174
+ [2024-11-11 14:45:50,292][00562] Num frames 2700...
1175
+ [2024-11-11 14:45:50,418][00562] Num frames 2800...
1176
+ [2024-11-11 14:45:50,548][00562] Num frames 2900...
1177
+ [2024-11-11 14:45:50,672][00562] Num frames 3000...
1178
+ [2024-11-11 14:45:50,795][00562] Num frames 3100...
1179
+ [2024-11-11 14:45:50,918][00562] Num frames 3200...
1180
+ [2024-11-11 14:45:51,039][00562] Num frames 3300...
1181
+ [2024-11-11 14:45:51,166][00562] Num frames 3400...
1182
+ [2024-11-11 14:45:51,294][00562] Num frames 3500...
1183
+ [2024-11-11 14:45:51,420][00562] Num frames 3600...
1184
+ [2024-11-11 14:45:51,542][00562] Num frames 3700...
1185
+ [2024-11-11 14:45:51,670][00562] Num frames 3800...
1186
+ [2024-11-11 14:45:51,796][00562] Num frames 3900...
1187
+ [2024-11-11 14:45:51,916][00562] Num frames 4000...
1188
+ [2024-11-11 14:45:52,040][00562] Num frames 4100...
1189
+ [2024-11-11 14:45:52,176][00562] Num frames 4200...
1190
+ [2024-11-11 14:45:52,228][00562] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000
1191
+ [2024-11-11 14:45:52,230][00562] Avg episode reward: 63.999, avg true_objective: 21.000
1192
+ [2024-11-11 14:45:52,363][00562] Num frames 4300...
1193
+ [2024-11-11 14:45:52,491][00562] Num frames 4400...
1194
+ [2024-11-11 14:45:52,625][00562] Num frames 4500...
1195
+ [2024-11-11 14:45:52,786][00562] Num frames 4600...
1196
+ [2024-11-11 14:45:52,956][00562] Num frames 4700...
1197
+ [2024-11-11 14:45:53,124][00562] Num frames 4800...
1198
+ [2024-11-11 14:45:53,284][00562] Num frames 4900...
1199
+ [2024-11-11 14:45:53,450][00562] Num frames 5000...
1200
+ [2024-11-11 14:45:53,623][00562] Num frames 5100...
1201
+ [2024-11-11 14:45:53,794][00562] Num frames 5200...
1202
+ [2024-11-11 14:45:53,959][00562] Num frames 5300...
1203
+ [2024-11-11 14:45:54,134][00562] Num frames 5400...
1204
+ [2024-11-11 14:45:54,309][00562] Num frames 5500...
1205
+ [2024-11-11 14:45:54,499][00562] Num frames 5600...
1206
+ [2024-11-11 14:45:54,676][00562] Num frames 5700...
1207
+ [2024-11-11 14:45:54,861][00562] Num frames 5800...
1208
+ [2024-11-11 14:45:55,035][00562] Num frames 5900...
1209
+ [2024-11-11 14:45:55,207][00562] Num frames 6000...
1210
+ [2024-11-11 14:45:55,329][00562] Num frames 6100...
1211
+ [2024-11-11 14:45:55,453][00562] Num frames 6200...
1212
+ [2024-11-11 14:45:55,580][00562] Num frames 6300...
1213
+ [2024-11-11 14:45:55,633][00562] Avg episode rewards: #0: 65.332, true rewards: #0: 21.000
1214
+ [2024-11-11 14:45:55,634][00562] Avg episode reward: 65.332, avg true_objective: 21.000
1215
+ [2024-11-11 14:45:55,771][00562] Num frames 6400...
1216
+ [2024-11-11 14:45:55,897][00562] Num frames 6500...
1217
+ [2024-11-11 14:45:56,019][00562] Num frames 6600...
1218
+ [2024-11-11 14:45:56,148][00562] Num frames 6700...
1219
+ [2024-11-11 14:45:56,271][00562] Num frames 6800...
1220
+ [2024-11-11 14:45:56,393][00562] Num frames 6900...
1221
+ [2024-11-11 14:45:56,515][00562] Num frames 7000...
1222
+ [2024-11-11 14:45:56,636][00562] Num frames 7100...
1223
+ [2024-11-11 14:45:56,756][00562] Num frames 7200...
1224
+ [2024-11-11 14:45:56,884][00562] Num frames 7300...
1225
+ [2024-11-11 14:45:57,003][00562] Num frames 7400...
1226
+ [2024-11-11 14:45:57,131][00562] Num frames 7500...
1227
+ [2024-11-11 14:45:57,251][00562] Num frames 7600...
1228
+ [2024-11-11 14:45:57,375][00562] Num frames 7700...
1229
+ [2024-11-11 14:45:57,497][00562] Num frames 7800...
1230
+ [2024-11-11 14:45:57,621][00562] Num frames 7900...
1231
+ [2024-11-11 14:45:57,772][00562] Num frames 8000...
1232
+ [2024-11-11 14:45:57,908][00562] Num frames 8100...
1233
+ [2024-11-11 14:45:58,033][00562] Num frames 8200...
1234
+ [2024-11-11 14:45:58,171][00562] Num frames 8300...
1235
+ [2024-11-11 14:45:58,304][00562] Num frames 8400...
1236
+ [2024-11-11 14:45:58,356][00562] Avg episode rewards: #0: 65.499, true rewards: #0: 21.000
1237
+ [2024-11-11 14:45:58,358][00562] Avg episode reward: 65.499, avg true_objective: 21.000
1238
+ [2024-11-11 14:45:58,482][00562] Num frames 8500...
1239
+ [2024-11-11 14:45:58,607][00562] Num frames 8600...
1240
+ [2024-11-11 14:45:58,727][00562] Num frames 8700...
1241
+ [2024-11-11 14:45:58,857][00562] Num frames 8800...
1242
+ [2024-11-11 14:45:58,986][00562] Num frames 8900...
1243
+ [2024-11-11 14:45:59,121][00562] Num frames 9000...
1244
+ [2024-11-11 14:45:59,242][00562] Num frames 9100...
1245
+ [2024-11-11 14:45:59,368][00562] Num frames 9200...
1246
+ [2024-11-11 14:45:59,499][00562] Num frames 9300...
1247
+ [2024-11-11 14:45:59,621][00562] Num frames 9400...
1248
+ [2024-11-11 14:45:59,745][00562] Num frames 9500...
1249
+ [2024-11-11 14:45:59,873][00562] Num frames 9600...
1250
+ [2024-11-11 14:45:59,998][00562] Num frames 9700...
1251
+ [2024-11-11 14:46:00,127][00562] Num frames 9800...
1252
+ [2024-11-11 14:46:00,247][00562] Num frames 9900...
1253
+ [2024-11-11 14:46:00,371][00562] Num frames 10000...
1254
+ [2024-11-11 14:46:00,494][00562] Num frames 10100...
1255
+ [2024-11-11 14:46:00,616][00562] Num frames 10200...
1256
+ [2024-11-11 14:46:00,738][00562] Num frames 10300...
1257
+ [2024-11-11 14:46:00,860][00562] Num frames 10400...
1258
+ [2024-11-11 14:46:00,995][00562] Num frames 10500...
1259
+ [2024-11-11 14:46:01,047][00562] Avg episode rewards: #0: 65.399, true rewards: #0: 21.000
1260
+ [2024-11-11 14:46:01,049][00562] Avg episode reward: 65.399, avg true_objective: 21.000
1261
+ [2024-11-11 14:46:01,179][00562] Num frames 10600...
1262
+ [2024-11-11 14:46:01,304][00562] Num frames 10700...
1263
+ [2024-11-11 14:46:01,428][00562] Num frames 10800...
1264
+ [2024-11-11 14:46:01,550][00562] Num frames 10900...
1265
+ [2024-11-11 14:46:01,672][00562] Num frames 11000...
1266
+ [2024-11-11 14:46:01,797][00562] Num frames 11100...
1267
+ [2024-11-11 14:46:01,927][00562] Num frames 11200...
1268
+ [2024-11-11 14:46:02,050][00562] Num frames 11300...
1269
+ [2024-11-11 14:46:02,182][00562] Num frames 11400...
1270
+ [2024-11-11 14:46:02,308][00562] Num frames 11500...
1271
+ [2024-11-11 14:46:02,435][00562] Num frames 11600...
1272
+ [2024-11-11 14:46:02,559][00562] Num frames 11700...
1273
+ [2024-11-11 14:46:02,685][00562] Num frames 11800...
1274
+ [2024-11-11 14:46:02,810][00562] Num frames 11900...
1275
+ [2024-11-11 14:46:02,935][00562] Num frames 12000...
1276
+ [2024-11-11 14:46:03,064][00562] Num frames 12100...
1277
+ [2024-11-11 14:46:03,194][00562] Num frames 12200...
1278
+ [2024-11-11 14:46:03,319][00562] Num frames 12300...
1279
+ [2024-11-11 14:46:03,458][00562] Num frames 12400...
1280
+ [2024-11-11 14:46:03,581][00562] Num frames 12500...
1281
+ [2024-11-11 14:46:03,712][00562] Num frames 12600...
1282
+ [2024-11-11 14:46:03,765][00562] Avg episode rewards: #0: 65.499, true rewards: #0: 21.000
1283
+ [2024-11-11 14:46:03,767][00562] Avg episode reward: 65.499, avg true_objective: 21.000
1284
+ [2024-11-11 14:46:03,893][00562] Num frames 12700...
1285
+ [2024-11-11 14:46:04,027][00562] Num frames 12800...
1286
+ [2024-11-11 14:46:04,159][00562] Num frames 12900...
1287
+ [2024-11-11 14:46:04,286][00562] Num frames 13000...
1288
+ [2024-11-11 14:46:04,409][00562] Num frames 13100...
1289
+ [2024-11-11 14:46:04,532][00562] Num frames 13200...
1290
+ [2024-11-11 14:46:04,656][00562] Num frames 13300...
1291
+ [2024-11-11 14:46:04,781][00562] Num frames 13400...
1292
+ [2024-11-11 14:46:04,904][00562] Num frames 13500...
1293
+ [2024-11-11 14:46:05,035][00562] Num frames 13600...
1294
+ [2024-11-11 14:46:05,176][00562] Num frames 13700...
1295
+ [2024-11-11 14:46:05,376][00562] Num frames 13800...
1296
+ [2024-11-11 14:46:05,564][00562] Num frames 13900...
1297
+ [2024-11-11 14:46:05,734][00562] Num frames 14000...
1298
+ [2024-11-11 14:46:05,905][00562] Num frames 14100...
1299
+ [2024-11-11 14:46:06,082][00562] Num frames 14200...
1300
+ [2024-11-11 14:46:06,249][00562] Num frames 14300...
1301
+ [2024-11-11 14:46:06,422][00562] Num frames 14400...
1302
+ [2024-11-11 14:46:06,597][00562] Num frames 14500...
1303
+ [2024-11-11 14:46:06,775][00562] Num frames 14600...
1304
+ [2024-11-11 14:46:06,950][00562] Num frames 14700...
1305
+ [2024-11-11 14:46:07,005][00562] Avg episode rewards: #0: 65.427, true rewards: #0: 21.000
1306
+ [2024-11-11 14:46:07,007][00562] Avg episode reward: 65.427, avg true_objective: 21.000
1307
+ [2024-11-11 14:46:07,194][00562] Num frames 14800...
1308
+ [2024-11-11 14:46:07,367][00562] Num frames 14900...
1309
+ [2024-11-11 14:46:07,538][00562] Num frames 15000...
1310
+ [2024-11-11 14:46:07,719][00562] Num frames 15100...
1311
+ [2024-11-11 14:46:07,869][00562] Num frames 15200...
1312
+ [2024-11-11 14:46:07,991][00562] Num frames 15300...
1313
+ [2024-11-11 14:46:08,126][00562] Num frames 15400...
1314
+ [2024-11-11 14:46:08,250][00562] Num frames 15500...
1315
+ [2024-11-11 14:46:08,373][00562] Num frames 15600...
1316
+ [2024-11-11 14:46:08,503][00562] Num frames 15700...
1317
+ [2024-11-11 14:46:08,628][00562] Num frames 15800...
1318
+ [2024-11-11 14:46:08,753][00562] Num frames 15900...
1319
+ [2024-11-11 14:46:08,878][00562] Num frames 16000...
1320
+ [2024-11-11 14:46:09,002][00562] Num frames 16100...
1321
+ [2024-11-11 14:46:09,140][00562] Num frames 16200...
1322
+ [2024-11-11 14:46:09,264][00562] Num frames 16300...
1323
+ [2024-11-11 14:46:09,397][00562] Num frames 16400...
1324
+ [2024-11-11 14:46:09,524][00562] Num frames 16500...
1325
+ [2024-11-11 14:46:09,653][00562] Num frames 16600...
1326
+ [2024-11-11 14:46:09,778][00562] Num frames 16700...
1327
+ [2024-11-11 14:46:09,906][00562] Num frames 16800...
1328
+ [2024-11-11 14:46:09,958][00562] Avg episode rewards: #0: 64.874, true rewards: #0: 21.000
1329
+ [2024-11-11 14:46:09,960][00562] Avg episode reward: 64.874, avg true_objective: 21.000
1330
+ [2024-11-11 14:46:10,082][00562] Num frames 16900...
1331
+ [2024-11-11 14:46:10,220][00562] Num frames 17000...
1332
+ [2024-11-11 14:46:10,344][00562] Num frames 17100...
1333
+ [2024-11-11 14:46:10,468][00562] Num frames 17200...
1334
+ [2024-11-11 14:46:10,589][00562] Num frames 17300...
1335
+ [2024-11-11 14:46:10,713][00562] Num frames 17400...
1336
+ [2024-11-11 14:46:10,835][00562] Num frames 17500...
1337
+ [2024-11-11 14:46:10,962][00562] Num frames 17600...
1338
+ [2024-11-11 14:46:11,086][00562] Num frames 17700...
1339
+ [2024-11-11 14:46:11,224][00562] Num frames 17800...
1340
+ [2024-11-11 14:46:11,348][00562] Num frames 17900...
1341
+ [2024-11-11 14:46:11,471][00562] Num frames 18000...
1342
+ [2024-11-11 14:46:11,596][00562] Num frames 18100...
1343
+ [2024-11-11 14:46:11,719][00562] Num frames 18200...
1344
+ [2024-11-11 14:46:11,843][00562] Num frames 18300...
1345
+ [2024-11-11 14:46:11,906][00562] Avg episode rewards: #0: 62.670, true rewards: #0: 20.338
1346
+ [2024-11-11 14:46:11,908][00562] Avg episode reward: 62.670, avg true_objective: 20.338
1347
+ [2024-11-11 14:46:12,031][00562] Num frames 18400...
1348
+ [2024-11-11 14:46:12,163][00562] Num frames 18500...
1349
+ [2024-11-11 14:46:12,293][00562] Num frames 18600...
1350
+ [2024-11-11 14:46:12,421][00562] Num frames 18700...
1351
+ [2024-11-11 14:46:12,544][00562] Num frames 18800...
1352
+ [2024-11-11 14:46:12,665][00562] Num frames 18900...
1353
+ [2024-11-11 14:46:12,792][00562] Num frames 19000...
1354
+ [2024-11-11 14:46:12,897][00562] Avg episode rewards: #0: 57.739, true rewards: #0: 19.040
1355
+ [2024-11-11 14:46:12,899][00562] Avg episode reward: 57.739, avg true_objective: 19.040
1356
+ [2024-11-11 14:48:09,151][00562] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
1357
+ [2024-11-11 14:50:05,788][00562] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
1358
+ [2024-11-11 14:50:05,790][00562] Overriding arg 'num_workers' with value 1 passed from command line
1359
+ [2024-11-11 14:50:05,791][00562] Adding new argument 'no_render'=True that is not in the saved config file!
1360
+ [2024-11-11 14:50:05,793][00562] Adding new argument 'save_video'=True that is not in the saved config file!
1361
+ [2024-11-11 14:50:05,795][00562] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1362
+ [2024-11-11 14:50:05,796][00562] Adding new argument 'video_name'=None that is not in the saved config file!
1363
+ [2024-11-11 14:50:05,797][00562] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
1364
+ [2024-11-11 14:50:05,799][00562] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1365
+ [2024-11-11 14:50:05,800][00562] Adding new argument 'push_to_hub'=True that is not in the saved config file!
1366
+ [2024-11-11 14:50:05,802][00562] Adding new argument 'hf_repository'='usamabuttar/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
1367
+ [2024-11-11 14:50:05,803][00562] Adding new argument 'policy_index'=0 that is not in the saved config file!
1368
+ [2024-11-11 14:50:05,808][00562] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1369
+ [2024-11-11 14:50:05,809][00562] Adding new argument 'train_script'=None that is not in the saved config file!
1370
+ [2024-11-11 14:50:05,810][00562] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1371
+ [2024-11-11 14:50:05,811][00562] Using frameskip 1 and render_action_repeat=4 for evaluation
1372
+ [2024-11-11 14:50:05,840][00562] RunningMeanStd input shape: (3, 72, 128)
1373
+ [2024-11-11 14:50:05,841][00562] RunningMeanStd input shape: (1,)
1374
+ [2024-11-11 14:50:05,855][00562] ConvEncoder: input_channels=3
1375
+ [2024-11-11 14:50:05,894][00562] Conv encoder output size: 512
1376
+ [2024-11-11 14:50:05,896][00562] Policy head output size: 512
1377
+ [2024-11-11 14:50:05,914][00562] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
1378
+ [2024-11-11 14:50:06,364][00562] Num frames 100...
1379
+ [2024-11-11 14:50:06,482][00562] Num frames 200...
1380
+ [2024-11-11 14:50:06,601][00562] Num frames 300...
1381
+ [2024-11-11 14:50:06,722][00562] Num frames 400...
1382
+ [2024-11-11 14:50:06,848][00562] Num frames 500...
1383
+ [2024-11-11 14:50:06,972][00562] Num frames 600...
1384
+ [2024-11-11 14:50:07,093][00562] Num frames 700...
1385
+ [2024-11-11 14:50:07,215][00562] Num frames 800...
1386
+ [2024-11-11 14:50:07,333][00562] Num frames 900...
1387
+ [2024-11-11 14:50:07,455][00562] Num frames 1000...
1388
+ [2024-11-11 14:50:07,596][00562] Avg episode rewards: #0: 23.690, true rewards: #0: 10.690
1389
+ [2024-11-11 14:50:07,598][00562] Avg episode reward: 23.690, avg true_objective: 10.690
1390
+ [2024-11-11 14:50:07,638][00562] Num frames 1100...
1391
+ [2024-11-11 14:50:07,756][00562] Num frames 1200...
1392
+ [2024-11-11 14:50:07,880][00562] Num frames 1300...
1393
+ [2024-11-11 14:50:08,006][00562] Num frames 1400...
1394
+ [2024-11-11 14:50:08,129][00562] Num frames 1500...
1395
+ [2024-11-11 14:50:08,246][00562] Num frames 1600...
1396
+ [2024-11-11 14:50:08,364][00562] Num frames 1700...
1397
+ [2024-11-11 14:50:08,484][00562] Num frames 1800...
1398
+ [2024-11-11 14:50:08,605][00562] Num frames 1900...
1399
+ [2024-11-11 14:50:08,727][00562] Num frames 2000...
1400
+ [2024-11-11 14:50:08,854][00562] Num frames 2100...
1401
+ [2024-11-11 14:50:08,982][00562] Num frames 2200...
1402
+ [2024-11-11 14:50:09,078][00562] Avg episode rewards: #0: 24.160, true rewards: #0: 11.160
1403
+ [2024-11-11 14:50:09,080][00562] Avg episode reward: 24.160, avg true_objective: 11.160
1404
+ [2024-11-11 14:50:09,171][00562] Num frames 2300...
1405
+ [2024-11-11 14:50:09,291][00562] Num frames 2400...
1406
+ [2024-11-11 14:50:09,412][00562] Num frames 2500...
1407
+ [2024-11-11 14:50:09,535][00562] Num frames 2600...
1408
+ [2024-11-11 14:50:09,658][00562] Num frames 2700...
1409
+ [2024-11-11 14:50:09,781][00562] Num frames 2800...
1410
+ [2024-11-11 14:50:09,909][00562] Num frames 2900...
1411
+ [2024-11-11 14:50:10,031][00562] Num frames 3000...
1412
+ [2024-11-11 14:50:10,159][00562] Num frames 3100...
1413
+ [2024-11-11 14:50:10,278][00562] Num frames 3200...
1414
+ [2024-11-11 14:50:10,401][00562] Num frames 3300...
1415
+ [2024-11-11 14:50:10,525][00562] Num frames 3400...
1416
+ [2024-11-11 14:50:10,647][00562] Num frames 3500...
1417
+ [2024-11-11 14:50:10,766][00562] Num frames 3600...
1418
+ [2024-11-11 14:50:10,889][00562] Num frames 3700...
1419
+ [2024-11-11 14:50:11,058][00562] Num frames 3800...
1420
+ [2024-11-11 14:50:11,236][00562] Num frames 3900...
1421
+ [2024-11-11 14:50:11,402][00562] Num frames 4000...
1422
+ [2024-11-11 14:50:11,574][00562] Num frames 4100...
1423
+ [2024-11-11 14:50:11,740][00562] Num frames 4200...
1424
+ [2024-11-11 14:50:11,908][00562] Num frames 4300...
1425
+ [2024-11-11 14:50:12,024][00562] Avg episode rewards: #0: 34.440, true rewards: #0: 14.440
1426
+ [2024-11-11 14:50:12,028][00562] Avg episode reward: 34.440, avg true_objective: 14.440
1427
+ [2024-11-11 14:50:12,154][00562] Num frames 4400...
1428
+ [2024-11-11 14:50:12,323][00562] Num frames 4500...
1429
+ [2024-11-11 14:50:12,489][00562] Num frames 4600...
1430
+ [2024-11-11 14:50:12,660][00562] Num frames 4700...
1431
+ [2024-11-11 14:50:12,831][00562] Num frames 4800...
1432
+ [2024-11-11 14:50:13,006][00562] Num frames 4900...
1433
+ [2024-11-11 14:50:13,180][00562] Num frames 5000...
1434
+ [2024-11-11 14:50:13,351][00562] Num frames 5100...
1435
+ [2024-11-11 14:50:13,502][00562] Num frames 5200...
1436
+ [2024-11-11 14:50:13,618][00562] Num frames 5300...
1437
+ [2024-11-11 14:50:13,741][00562] Num frames 5400...
1438
+ [2024-11-11 14:50:13,878][00562] Num frames 5500...
1439
+ [2024-11-11 14:50:14,014][00562] Num frames 5600...
1440
+ [2024-11-11 14:50:14,143][00562] Num frames 5700...
1441
+ [2024-11-11 14:50:14,265][00562] Num frames 5800...
1442
+ [2024-11-11 14:50:14,385][00562] Num frames 5900...
1443
+ [2024-11-11 14:50:14,503][00562] Num frames 6000...
1444
+ [2024-11-11 14:50:14,622][00562] Num frames 6100...
1445
+ [2024-11-11 14:50:14,742][00562] Num frames 6200...
1446
+ [2024-11-11 14:50:14,862][00562] Num frames 6300...
1447
+ [2024-11-11 14:50:14,983][00562] Num frames 6400...
1448
+ [2024-11-11 14:50:15,077][00562] Avg episode rewards: #0: 40.329, true rewards: #0: 16.080
1449
+ [2024-11-11 14:50:15,079][00562] Avg episode reward: 40.329, avg true_objective: 16.080
1450
+ [2024-11-11 14:50:15,166][00562] Num frames 6500...
1451
+ [2024-11-11 14:50:15,282][00562] Num frames 6600...
1452
+ [2024-11-11 14:50:15,406][00562] Num frames 6700...
1453
+ [2024-11-11 14:50:15,525][00562] Num frames 6800...
1454
+ [2024-11-11 14:50:15,644][00562] Num frames 6900...
1455
+ [2024-11-11 14:50:15,765][00562] Num frames 7000...
1456
+ [2024-11-11 14:50:15,883][00562] Num frames 7100...
1457
+ [2024-11-11 14:50:16,005][00562] Num frames 7200...
1458
+ [2024-11-11 14:50:16,202][00562] Avg episode rewards: #0: 35.794, true rewards: #0: 14.594
1459
+ [2024-11-11 14:50:16,204][00562] Avg episode reward: 35.794, avg true_objective: 14.594
1460
+ [2024-11-11 14:50:16,211][00562] Num frames 7300...
1461
+ [2024-11-11 14:50:16,329][00562] Num frames 7400...
1462
+ [2024-11-11 14:50:16,450][00562] Num frames 7500...
1463
+ [2024-11-11 14:50:16,570][00562] Num frames 7600...
1464
+ [2024-11-11 14:50:16,691][00562] Num frames 7700...
1465
+ [2024-11-11 14:50:16,819][00562] Num frames 7800...
1466
+ [2024-11-11 14:50:16,936][00562] Num frames 7900...
1467
+ [2024-11-11 14:50:17,074][00562] Num frames 8000...
1468
+ [2024-11-11 14:50:17,210][00562] Num frames 8100...
1469
+ [2024-11-11 14:50:17,327][00562] Num frames 8200...
1470
+ [2024-11-11 14:50:17,452][00562] Num frames 8300...
1471
+ [2024-11-11 14:50:17,571][00562] Num frames 8400...
1472
+ [2024-11-11 14:50:17,648][00562] Avg episode rewards: #0: 33.528, true rewards: #0: 14.028
1473
+ [2024-11-11 14:50:17,649][00562] Avg episode reward: 33.528, avg true_objective: 14.028
1474
+ [2024-11-11 14:50:17,750][00562] Num frames 8500...
1475
+ [2024-11-11 14:50:17,866][00562] Num frames 8600...
1476
+ [2024-11-11 14:50:17,984][00562] Num frames 8700...
1477
+ [2024-11-11 14:50:18,117][00562] Num frames 8800...
1478
+ [2024-11-11 14:50:18,251][00562] Avg episode rewards: #0: 29.521, true rewards: #0: 12.664
1479
+ [2024-11-11 14:50:18,253][00562] Avg episode reward: 29.521, avg true_objective: 12.664
1480
+ [2024-11-11 14:50:18,295][00562] Num frames 8900...
1481
+ [2024-11-11 14:50:18,411][00562] Num frames 9000...
1482
+ [2024-11-11 14:50:18,530][00562] Num frames 9100...
1483
+ [2024-11-11 14:50:18,654][00562] Num frames 9200...
1484
+ [2024-11-11 14:50:18,768][00562] Avg episode rewards: #0: 26.311, true rewards: #0: 11.561
1485
+ [2024-11-11 14:50:18,770][00562] Avg episode reward: 26.311, avg true_objective: 11.561
1486
+ [2024-11-11 14:50:18,837][00562] Num frames 9300...
1487
+ [2024-11-11 14:50:18,960][00562] Num frames 9400...
1488
+ [2024-11-11 14:50:19,081][00562] Num frames 9500...
1489
+ [2024-11-11 14:50:19,221][00562] Num frames 9600...
1490
+ [2024-11-11 14:50:19,339][00562] Num frames 9700...
1491
+ [2024-11-11 14:50:19,458][00562] Num frames 9800...
1492
+ [2024-11-11 14:50:19,579][00562] Num frames 9900...
1493
+ [2024-11-11 14:50:19,698][00562] Num frames 10000...
1494
+ [2024-11-11 14:50:19,819][00562] Num frames 10100...
1495
+ [2024-11-11 14:50:19,975][00562] Avg episode rewards: #0: 25.426, true rewards: #0: 11.316
1496
+ [2024-11-11 14:50:19,977][00562] Avg episode reward: 25.426, avg true_objective: 11.316
1497
+ [2024-11-11 14:50:19,999][00562] Num frames 10200...
1498
+ [2024-11-11 14:50:20,124][00562] Num frames 10300...
1499
+ [2024-11-11 14:50:20,252][00562] Num frames 10400...
1500
+ [2024-11-11 14:50:20,374][00562] Num frames 10500...
1501
+ [2024-11-11 14:50:20,497][00562] Num frames 10600...
1502
+ [2024-11-11 14:50:20,617][00562] Num frames 10700...
1503
+ [2024-11-11 14:50:20,739][00562] Num frames 10800...
1504
+ [2024-11-11 14:50:20,863][00562] Avg episode rewards: #0: 24.356, true rewards: #0: 10.856
1505
+ [2024-11-11 14:50:20,865][00562] Avg episode reward: 24.356, avg true_objective: 10.856
1506
+ [2024-11-11 14:51:25,155][00562] Replay video saved to /content/train_dir/default_experiment/replay.mp4!