yhyeo0202 commited on
Commit
e587e03
1 Parent(s): 4e83cb0

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 +520 -0
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 9.03 +/- 4.98
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 9.69 +/- 4.26
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:b5c6980350bc2663c6061352aaead54b5ddb089cb3299ee65dd2f9a240be4fc5
3
- size 17314494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef16baae3dfc8b7adadfabe54aa6347964542d5d5c3954a7e4b80aa144303f36
3
+ size 18844234
sf_log.txt CHANGED
@@ -1128,3 +1128,523 @@ main_loop: 1273.3851
1128
  [2024-09-21 13:24:58,375][00197] Avg episode rewards: #0: 20.328, true rewards: #0: 9.028
1129
  [2024-09-21 13:24:58,376][00197] Avg episode reward: 20.328, avg true_objective: 9.028
1130
  [2024-09-21 13:25:58,200][00197] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1128
  [2024-09-21 13:24:58,375][00197] Avg episode rewards: #0: 20.328, true rewards: #0: 9.028
1129
  [2024-09-21 13:24:58,376][00197] Avg episode reward: 20.328, avg true_objective: 9.028
1130
  [2024-09-21 13:25:58,200][00197] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
1131
+ [2024-09-21 13:26:03,118][00197] The model has been pushed to https://huggingface.co/yhyeo0202/rl_course_vizdoom_health_gathering_supreme
1132
+ [2024-09-21 13:29:37,213][00197] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
1133
+ [2024-09-21 13:29:37,216][00197] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
1134
+ [2024-09-21 13:29:37,218][00197] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
1135
+ [2024-09-21 13:29:37,222][00197] Overriding arg 'train_dir' with value 'train_dir' passed from command line
1136
+ [2024-09-21 13:29:37,225][00197] Overriding arg 'num_workers' with value 1 passed from command line
1137
+ [2024-09-21 13:29:37,227][00197] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
1138
+ [2024-09-21 13:29:37,229][00197] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
1139
+ [2024-09-21 13:29:37,231][00197] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
1140
+ [2024-09-21 13:29:37,232][00197] Adding new argument 'no_render'=True that is not in the saved config file!
1141
+ [2024-09-21 13:29:37,233][00197] Adding new argument 'save_video'=True that is not in the saved config file!
1142
+ [2024-09-21 13:29:37,234][00197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1143
+ [2024-09-21 13:29:37,235][00197] Adding new argument 'video_name'=None that is not in the saved config file!
1144
+ [2024-09-21 13:29:37,236][00197] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
1145
+ [2024-09-21 13:29:37,241][00197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1146
+ [2024-09-21 13:29:37,242][00197] Adding new argument 'push_to_hub'=False that is not in the saved config file!
1147
+ [2024-09-21 13:29:37,243][00197] Adding new argument 'hf_repository'=None that is not in the saved config file!
1148
+ [2024-09-21 13:29:37,244][00197] Adding new argument 'policy_index'=0 that is not in the saved config file!
1149
+ [2024-09-21 13:29:37,245][00197] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1150
+ [2024-09-21 13:29:37,246][00197] Adding new argument 'train_script'=None that is not in the saved config file!
1151
+ [2024-09-21 13:29:37,247][00197] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1152
+ [2024-09-21 13:29:37,248][00197] Using frameskip 1 and render_action_repeat=4 for evaluation
1153
+ [2024-09-21 13:29:37,267][00197] RunningMeanStd input shape: (3, 72, 128)
1154
+ [2024-09-21 13:29:37,269][00197] RunningMeanStd input shape: (1,)
1155
+ [2024-09-21 13:29:37,309][00197] ConvEncoder: input_channels=3
1156
+ [2024-09-21 13:29:37,386][00197] Conv encoder output size: 512
1157
+ [2024-09-21 13:29:37,388][00197] Policy head output size: 512
1158
+ [2024-09-21 13:29:37,426][00197] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
1159
+ [2024-09-21 13:29:38,229][00197] Num frames 100...
1160
+ [2024-09-21 13:29:38,429][00197] Num frames 200...
1161
+ [2024-09-21 13:29:38,588][00197] Num frames 300...
1162
+ [2024-09-21 13:29:38,715][00197] Num frames 400...
1163
+ [2024-09-21 13:29:38,849][00197] Num frames 500...
1164
+ [2024-09-21 13:29:38,975][00197] Num frames 600...
1165
+ [2024-09-21 13:29:39,106][00197] Num frames 700...
1166
+ [2024-09-21 13:29:39,232][00197] Num frames 800...
1167
+ [2024-09-21 13:29:39,369][00197] Num frames 900...
1168
+ [2024-09-21 13:29:39,498][00197] Num frames 1000...
1169
+ [2024-09-21 13:29:39,623][00197] Num frames 1100...
1170
+ [2024-09-21 13:29:39,756][00197] Num frames 1200...
1171
+ [2024-09-21 13:29:39,894][00197] Num frames 1300...
1172
+ [2024-09-21 13:29:40,020][00197] Num frames 1400...
1173
+ [2024-09-21 13:29:40,152][00197] Num frames 1500...
1174
+ [2024-09-21 13:29:40,291][00197] Num frames 1600...
1175
+ [2024-09-21 13:29:40,433][00197] Num frames 1700...
1176
+ [2024-09-21 13:29:40,571][00197] Num frames 1800...
1177
+ [2024-09-21 13:29:40,731][00197] Num frames 1900...
1178
+ [2024-09-21 13:29:40,866][00197] Num frames 2000...
1179
+ [2024-09-21 13:29:41,006][00197] Num frames 2100...
1180
+ [2024-09-21 13:29:41,058][00197] Avg episode rewards: #0: 65.999, true rewards: #0: 21.000
1181
+ [2024-09-21 13:29:41,061][00197] Avg episode reward: 65.999, avg true_objective: 21.000
1182
+ [2024-09-21 13:29:41,201][00197] Num frames 2200...
1183
+ [2024-09-21 13:29:41,331][00197] Num frames 2300...
1184
+ [2024-09-21 13:29:41,470][00197] Num frames 2400...
1185
+ [2024-09-21 13:29:41,601][00197] Num frames 2500...
1186
+ [2024-09-21 13:29:41,726][00197] Num frames 2600...
1187
+ [2024-09-21 13:29:41,870][00197] Num frames 2700...
1188
+ [2024-09-21 13:29:41,998][00197] Num frames 2800...
1189
+ [2024-09-21 13:29:42,126][00197] Num frames 2900...
1190
+ [2024-09-21 13:29:42,264][00197] Num frames 3000...
1191
+ [2024-09-21 13:29:42,402][00197] Num frames 3100...
1192
+ [2024-09-21 13:29:42,542][00197] Num frames 3200...
1193
+ [2024-09-21 13:29:42,672][00197] Num frames 3300...
1194
+ [2024-09-21 13:29:42,802][00197] Num frames 3400...
1195
+ [2024-09-21 13:29:42,938][00197] Num frames 3500...
1196
+ [2024-09-21 13:29:43,078][00197] Num frames 3600...
1197
+ [2024-09-21 13:29:43,206][00197] Num frames 3700...
1198
+ [2024-09-21 13:29:43,338][00197] Num frames 3800...
1199
+ [2024-09-21 13:29:43,481][00197] Num frames 3900...
1200
+ [2024-09-21 13:29:43,613][00197] Num frames 4000...
1201
+ [2024-09-21 13:29:43,743][00197] Num frames 4100...
1202
+ [2024-09-21 13:29:43,889][00197] Num frames 4200...
1203
+ [2024-09-21 13:29:43,942][00197] Avg episode rewards: #0: 65.999, true rewards: #0: 21.000
1204
+ [2024-09-21 13:29:43,944][00197] Avg episode reward: 65.999, avg true_objective: 21.000
1205
+ [2024-09-21 13:29:44,073][00197] Num frames 4300...
1206
+ [2024-09-21 13:29:44,202][00197] Num frames 4400...
1207
+ [2024-09-21 13:29:44,339][00197] Num frames 4500...
1208
+ [2024-09-21 13:29:44,469][00197] Num frames 4600...
1209
+ [2024-09-21 13:29:44,613][00197] Num frames 4700...
1210
+ [2024-09-21 13:29:44,741][00197] Num frames 4800...
1211
+ [2024-09-21 13:29:44,880][00197] Num frames 4900...
1212
+ [2024-09-21 13:29:45,007][00197] Num frames 5000...
1213
+ [2024-09-21 13:29:45,145][00197] Num frames 5100...
1214
+ [2024-09-21 13:29:45,286][00197] Num frames 5200...
1215
+ [2024-09-21 13:29:45,418][00197] Num frames 5300...
1216
+ [2024-09-21 13:29:45,560][00197] Num frames 5400...
1217
+ [2024-09-21 13:29:45,690][00197] Num frames 5500...
1218
+ [2024-09-21 13:29:45,817][00197] Num frames 5600...
1219
+ [2024-09-21 13:29:45,956][00197] Num frames 5700...
1220
+ [2024-09-21 13:29:46,092][00197] Num frames 5800...
1221
+ [2024-09-21 13:29:46,225][00197] Num frames 5900...
1222
+ [2024-09-21 13:29:46,367][00197] Num frames 6000...
1223
+ [2024-09-21 13:29:46,498][00197] Num frames 6100...
1224
+ [2024-09-21 13:29:46,643][00197] Num frames 6200...
1225
+ [2024-09-21 13:29:46,771][00197] Num frames 6300...
1226
+ [2024-09-21 13:29:46,824][00197] Avg episode rewards: #0: 66.999, true rewards: #0: 21.000
1227
+ [2024-09-21 13:29:46,826][00197] Avg episode reward: 66.999, avg true_objective: 21.000
1228
+ [2024-09-21 13:29:46,970][00197] Num frames 6400...
1229
+ [2024-09-21 13:29:47,107][00197] Num frames 6500...
1230
+ [2024-09-21 13:29:47,237][00197] Num frames 6600...
1231
+ [2024-09-21 13:29:47,377][00197] Num frames 6700...
1232
+ [2024-09-21 13:29:47,515][00197] Num frames 6800...
1233
+ [2024-09-21 13:29:47,653][00197] Num frames 6900...
1234
+ [2024-09-21 13:29:47,776][00197] Num frames 7000...
1235
+ [2024-09-21 13:29:47,922][00197] Num frames 7100...
1236
+ [2024-09-21 13:29:48,059][00197] Num frames 7200...
1237
+ [2024-09-21 13:29:48,195][00197] Num frames 7300...
1238
+ [2024-09-21 13:29:48,330][00197] Num frames 7400...
1239
+ [2024-09-21 13:29:48,468][00197] Num frames 7500...
1240
+ [2024-09-21 13:29:48,637][00197] Num frames 7600...
1241
+ [2024-09-21 13:29:48,834][00197] Num frames 7700...
1242
+ [2024-09-21 13:29:49,024][00197] Num frames 7800...
1243
+ [2024-09-21 13:29:49,205][00197] Num frames 7900...
1244
+ [2024-09-21 13:29:49,394][00197] Num frames 8000...
1245
+ [2024-09-21 13:29:49,576][00197] Num frames 8100...
1246
+ [2024-09-21 13:29:49,771][00197] Num frames 8200...
1247
+ [2024-09-21 13:29:49,965][00197] Num frames 8300...
1248
+ [2024-09-21 13:29:50,156][00197] Num frames 8400...
1249
+ [2024-09-21 13:29:50,213][00197] Avg episode rewards: #0: 65.499, true rewards: #0: 21.000
1250
+ [2024-09-21 13:29:50,215][00197] Avg episode reward: 65.499, avg true_objective: 21.000
1251
+ [2024-09-21 13:29:50,403][00197] Num frames 8500...
1252
+ [2024-09-21 13:29:50,597][00197] Num frames 8600...
1253
+ [2024-09-21 13:29:50,786][00197] Num frames 8700...
1254
+ [2024-09-21 13:29:50,973][00197] Num frames 8800...
1255
+ [2024-09-21 13:29:51,156][00197] Num frames 8900...
1256
+ [2024-09-21 13:29:51,339][00197] Num frames 9000...
1257
+ [2024-09-21 13:29:51,484][00197] Num frames 9100...
1258
+ [2024-09-21 13:29:51,616][00197] Num frames 9200...
1259
+ [2024-09-21 13:29:51,751][00197] Num frames 9300...
1260
+ [2024-09-21 13:29:51,898][00197] Num frames 9400...
1261
+ [2024-09-21 13:29:52,031][00197] Num frames 9500...
1262
+ [2024-09-21 13:29:52,174][00197] Num frames 9600...
1263
+ [2024-09-21 13:29:52,309][00197] Num frames 9700...
1264
+ [2024-09-21 13:29:52,443][00197] Num frames 9800...
1265
+ [2024-09-21 13:29:52,575][00197] Num frames 9900...
1266
+ [2024-09-21 13:29:52,704][00197] Num frames 10000...
1267
+ [2024-09-21 13:29:52,838][00197] Num frames 10100...
1268
+ [2024-09-21 13:29:52,980][00197] Num frames 10200...
1269
+ [2024-09-21 13:29:53,108][00197] Num frames 10300...
1270
+ [2024-09-21 13:29:53,240][00197] Num frames 10400...
1271
+ [2024-09-21 13:29:53,380][00197] Num frames 10500...
1272
+ [2024-09-21 13:29:53,433][00197] Avg episode rewards: #0: 65.999, true rewards: #0: 21.000
1273
+ [2024-09-21 13:29:53,435][00197] Avg episode reward: 65.999, avg true_objective: 21.000
1274
+ [2024-09-21 13:29:53,579][00197] Num frames 10600...
1275
+ [2024-09-21 13:29:53,727][00197] Num frames 10700...
1276
+ [2024-09-21 13:29:53,876][00197] Num frames 10800...
1277
+ [2024-09-21 13:29:54,011][00197] Num frames 10900...
1278
+ [2024-09-21 13:29:54,142][00197] Num frames 11000...
1279
+ [2024-09-21 13:29:54,286][00197] Num frames 11100...
1280
+ [2024-09-21 13:29:54,412][00197] Num frames 11200...
1281
+ [2024-09-21 13:29:54,552][00197] Num frames 11300...
1282
+ [2024-09-21 13:29:54,693][00197] Num frames 11400...
1283
+ [2024-09-21 13:29:54,840][00197] Num frames 11500...
1284
+ [2024-09-21 13:29:54,985][00197] Num frames 11600...
1285
+ [2024-09-21 13:29:55,123][00197] Num frames 11700...
1286
+ [2024-09-21 13:29:55,259][00197] Num frames 11800...
1287
+ [2024-09-21 13:29:55,391][00197] Num frames 11900...
1288
+ [2024-09-21 13:29:55,520][00197] Num frames 12000...
1289
+ [2024-09-21 13:29:55,649][00197] Num frames 12100...
1290
+ [2024-09-21 13:29:55,777][00197] Num frames 12200...
1291
+ [2024-09-21 13:29:55,921][00197] Num frames 12300...
1292
+ [2024-09-21 13:29:56,060][00197] Num frames 12400...
1293
+ [2024-09-21 13:29:56,187][00197] Num frames 12500...
1294
+ [2024-09-21 13:29:56,329][00197] Num frames 12600...
1295
+ [2024-09-21 13:29:56,381][00197] Avg episode rewards: #0: 65.665, true rewards: #0: 21.000
1296
+ [2024-09-21 13:29:56,384][00197] Avg episode reward: 65.665, avg true_objective: 21.000
1297
+ [2024-09-21 13:29:56,515][00197] Num frames 12700...
1298
+ [2024-09-21 13:29:56,659][00197] Num frames 12800...
1299
+ [2024-09-21 13:29:56,791][00197] Num frames 12900...
1300
+ [2024-09-21 13:29:56,928][00197] Num frames 13000...
1301
+ [2024-09-21 13:29:57,063][00197] Num frames 13100...
1302
+ [2024-09-21 13:29:57,195][00197] Num frames 13200...
1303
+ [2024-09-21 13:29:57,333][00197] Num frames 13300...
1304
+ [2024-09-21 13:29:57,465][00197] Num frames 13400...
1305
+ [2024-09-21 13:29:57,605][00197] Num frames 13500...
1306
+ [2024-09-21 13:29:57,733][00197] Num frames 13600...
1307
+ [2024-09-21 13:29:57,872][00197] Num frames 13700...
1308
+ [2024-09-21 13:29:58,018][00197] Num frames 13800...
1309
+ [2024-09-21 13:29:58,151][00197] Num frames 13900...
1310
+ [2024-09-21 13:29:58,283][00197] Num frames 14000...
1311
+ [2024-09-21 13:29:58,422][00197] Num frames 14100...
1312
+ [2024-09-21 13:29:58,554][00197] Num frames 14200...
1313
+ [2024-09-21 13:29:58,696][00197] Num frames 14300...
1314
+ [2024-09-21 13:29:58,832][00197] Num frames 14400...
1315
+ [2024-09-21 13:29:58,969][00197] Num frames 14500...
1316
+ [2024-09-21 13:29:59,125][00197] Num frames 14600...
1317
+ [2024-09-21 13:29:59,267][00197] Num frames 14700...
1318
+ [2024-09-21 13:29:59,320][00197] Avg episode rewards: #0: 65.427, true rewards: #0: 21.000
1319
+ [2024-09-21 13:29:59,322][00197] Avg episode reward: 65.427, avg true_objective: 21.000
1320
+ [2024-09-21 13:29:59,448][00197] Num frames 14800...
1321
+ [2024-09-21 13:29:59,584][00197] Num frames 14900...
1322
+ [2024-09-21 13:29:59,710][00197] Num frames 15000...
1323
+ [2024-09-21 13:29:59,835][00197] Num frames 15100...
1324
+ [2024-09-21 13:29:59,977][00197] Num frames 15200...
1325
+ [2024-09-21 13:30:00,116][00197] Num frames 15300...
1326
+ [2024-09-21 13:30:00,260][00197] Num frames 15400...
1327
+ [2024-09-21 13:30:00,391][00197] Num frames 15500...
1328
+ [2024-09-21 13:30:00,521][00197] Num frames 15600...
1329
+ [2024-09-21 13:30:00,647][00197] Num frames 15700...
1330
+ [2024-09-21 13:30:00,777][00197] Num frames 15800...
1331
+ [2024-09-21 13:30:00,911][00197] Num frames 15900...
1332
+ [2024-09-21 13:30:01,040][00197] Num frames 16000...
1333
+ [2024-09-21 13:30:01,177][00197] Num frames 16100...
1334
+ [2024-09-21 13:30:01,313][00197] Num frames 16200...
1335
+ [2024-09-21 13:30:01,510][00197] Num frames 16300...
1336
+ [2024-09-21 13:30:01,690][00197] Num frames 16400...
1337
+ [2024-09-21 13:30:01,888][00197] Num frames 16500...
1338
+ [2024-09-21 13:30:02,070][00197] Num frames 16600...
1339
+ [2024-09-21 13:30:02,252][00197] Num frames 16700...
1340
+ [2024-09-21 13:30:02,436][00197] Num frames 16800...
1341
+ [2024-09-21 13:30:02,493][00197] Avg episode rewards: #0: 64.749, true rewards: #0: 21.000
1342
+ [2024-09-21 13:30:02,495][00197] Avg episode reward: 64.749, avg true_objective: 21.000
1343
+ [2024-09-21 13:30:02,685][00197] Num frames 16900...
1344
+ [2024-09-21 13:30:02,870][00197] Num frames 17000...
1345
+ [2024-09-21 13:30:03,063][00197] Num frames 17100...
1346
+ [2024-09-21 13:30:03,266][00197] Num frames 17200...
1347
+ [2024-09-21 13:30:03,450][00197] Num frames 17300...
1348
+ [2024-09-21 13:30:03,646][00197] Num frames 17400...
1349
+ [2024-09-21 13:30:03,845][00197] Num frames 17500...
1350
+ [2024-09-21 13:30:04,051][00197] Num frames 17600...
1351
+ [2024-09-21 13:30:04,205][00197] Num frames 17700...
1352
+ [2024-09-21 13:30:04,347][00197] Num frames 17800...
1353
+ [2024-09-21 13:30:04,474][00197] Num frames 17900...
1354
+ [2024-09-21 13:30:04,601][00197] Num frames 18000...
1355
+ [2024-09-21 13:30:04,735][00197] Num frames 18100...
1356
+ [2024-09-21 13:30:04,875][00197] Num frames 18200...
1357
+ [2024-09-21 13:30:05,007][00197] Num frames 18300...
1358
+ [2024-09-21 13:30:05,136][00197] Num frames 18400...
1359
+ [2024-09-21 13:30:05,282][00197] Num frames 18500...
1360
+ [2024-09-21 13:30:05,417][00197] Num frames 18600...
1361
+ [2024-09-21 13:30:05,546][00197] Num frames 18700...
1362
+ [2024-09-21 13:30:05,680][00197] Num frames 18800...
1363
+ [2024-09-21 13:30:05,808][00197] Num frames 18900...
1364
+ [2024-09-21 13:30:05,860][00197] Avg episode rewards: #0: 64.665, true rewards: #0: 21.000
1365
+ [2024-09-21 13:30:05,862][00197] Avg episode reward: 64.665, avg true_objective: 21.000
1366
+ [2024-09-21 13:30:05,992][00197] Num frames 19000...
1367
+ [2024-09-21 13:30:06,121][00197] Num frames 19100...
1368
+ [2024-09-21 13:30:06,250][00197] Num frames 19200...
1369
+ [2024-09-21 13:30:06,388][00197] Num frames 19300...
1370
+ [2024-09-21 13:30:06,522][00197] Num frames 19400...
1371
+ [2024-09-21 13:30:06,653][00197] Num frames 19500...
1372
+ [2024-09-21 13:30:06,783][00197] Num frames 19600...
1373
+ [2024-09-21 13:30:06,930][00197] Num frames 19700...
1374
+ [2024-09-21 13:30:07,062][00197] Num frames 19800...
1375
+ [2024-09-21 13:30:07,188][00197] Num frames 19900...
1376
+ [2024-09-21 13:30:07,330][00197] Num frames 20000...
1377
+ [2024-09-21 13:30:07,460][00197] Num frames 20100...
1378
+ [2024-09-21 13:30:07,589][00197] Num frames 20200...
1379
+ [2024-09-21 13:30:07,720][00197] Num frames 20300...
1380
+ [2024-09-21 13:30:07,856][00197] Num frames 20400...
1381
+ [2024-09-21 13:30:07,988][00197] Num frames 20500...
1382
+ [2024-09-21 13:30:08,126][00197] Num frames 20600...
1383
+ [2024-09-21 13:30:08,263][00197] Num frames 20700...
1384
+ [2024-09-21 13:30:08,405][00197] Num frames 20800...
1385
+ [2024-09-21 13:30:08,542][00197] Num frames 20900...
1386
+ [2024-09-21 13:30:08,682][00197] Num frames 21000...
1387
+ [2024-09-21 13:30:08,735][00197] Avg episode rewards: #0: 64.899, true rewards: #0: 21.000
1388
+ [2024-09-21 13:30:08,737][00197] Avg episode reward: 64.899, avg true_objective: 21.000
1389
+ [2024-09-21 13:32:23,807][00197] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
1390
+ [2024-09-21 13:46:20,436][00197] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
1391
+ [2024-09-21 13:46:20,438][00197] Overriding arg 'num_workers' with value 1 passed from command line
1392
+ [2024-09-21 13:46:20,440][00197] Adding new argument 'no_render'=True that is not in the saved config file!
1393
+ [2024-09-21 13:46:20,442][00197] Adding new argument 'save_video'=True that is not in the saved config file!
1394
+ [2024-09-21 13:46:20,443][00197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1395
+ [2024-09-21 13:46:20,445][00197] Adding new argument 'video_name'=None that is not in the saved config file!
1396
+ [2024-09-21 13:46:20,446][00197] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
1397
+ [2024-09-21 13:46:20,447][00197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1398
+ [2024-09-21 13:46:20,449][00197] Adding new argument 'push_to_hub'=True that is not in the saved config file!
1399
+ [2024-09-21 13:46:20,450][00197] Adding new argument 'hf_repository'='yhyeo0202/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
1400
+ [2024-09-21 13:46:20,452][00197] Adding new argument 'policy_index'=0 that is not in the saved config file!
1401
+ [2024-09-21 13:46:20,453][00197] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1402
+ [2024-09-21 13:46:20,455][00197] Adding new argument 'train_script'=None that is not in the saved config file!
1403
+ [2024-09-21 13:46:20,456][00197] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1404
+ [2024-09-21 13:46:20,458][00197] Using frameskip 1 and render_action_repeat=4 for evaluation
1405
+ [2024-09-21 13:46:20,476][00197] RunningMeanStd input shape: (3, 72, 128)
1406
+ [2024-09-21 13:46:20,479][00197] RunningMeanStd input shape: (1,)
1407
+ [2024-09-21 13:46:20,492][00197] ConvEncoder: input_channels=3
1408
+ [2024-09-21 13:46:20,529][00197] Conv encoder output size: 512
1409
+ [2024-09-21 13:46:20,532][00197] Policy head output size: 512
1410
+ [2024-09-21 13:46:20,554][00197] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
1411
+ [2024-09-21 13:46:21,077][00197] Num frames 100...
1412
+ [2024-09-21 13:46:21,203][00197] Num frames 200...
1413
+ [2024-09-21 13:46:21,327][00197] Num frames 300...
1414
+ [2024-09-21 13:46:21,451][00197] Num frames 400...
1415
+ [2024-09-21 13:46:21,575][00197] Num frames 500...
1416
+ [2024-09-21 13:46:21,697][00197] Num frames 600...
1417
+ [2024-09-21 13:46:21,834][00197] Num frames 700...
1418
+ [2024-09-21 13:46:21,963][00197] Num frames 800...
1419
+ [2024-09-21 13:46:22,099][00197] Avg episode rewards: #0: 15.640, true rewards: #0: 8.640
1420
+ [2024-09-21 13:46:22,101][00197] Avg episode reward: 15.640, avg true_objective: 8.640
1421
+ [2024-09-21 13:46:22,149][00197] Num frames 900...
1422
+ [2024-09-21 13:46:22,281][00197] Num frames 1000...
1423
+ [2024-09-21 13:46:22,462][00197] Num frames 1100...
1424
+ [2024-09-21 13:46:22,626][00197] Num frames 1200...
1425
+ [2024-09-21 13:46:22,804][00197] Num frames 1300...
1426
+ [2024-09-21 13:46:22,973][00197] Num frames 1400...
1427
+ [2024-09-21 13:46:23,149][00197] Num frames 1500...
1428
+ [2024-09-21 13:46:23,314][00197] Num frames 1600...
1429
+ [2024-09-21 13:46:23,485][00197] Num frames 1700...
1430
+ [2024-09-21 13:46:23,664][00197] Num frames 1800...
1431
+ [2024-09-21 13:46:23,854][00197] Num frames 1900...
1432
+ [2024-09-21 13:46:24,028][00197] Num frames 2000...
1433
+ [2024-09-21 13:46:24,212][00197] Num frames 2100...
1434
+ [2024-09-21 13:46:24,390][00197] Num frames 2200...
1435
+ [2024-09-21 13:46:24,566][00197] Num frames 2300...
1436
+ [2024-09-21 13:46:24,632][00197] Avg episode rewards: #0: 23.020, true rewards: #0: 11.520
1437
+ [2024-09-21 13:46:24,635][00197] Avg episode reward: 23.020, avg true_objective: 11.520
1438
+ [2024-09-21 13:46:24,823][00197] Num frames 2400...
1439
+ [2024-09-21 13:46:24,981][00197] Num frames 2500...
1440
+ [2024-09-21 13:46:25,106][00197] Num frames 2600...
1441
+ [2024-09-21 13:46:25,239][00197] Num frames 2700...
1442
+ [2024-09-21 13:46:25,373][00197] Num frames 2800...
1443
+ [2024-09-21 13:46:25,498][00197] Num frames 2900...
1444
+ [2024-09-21 13:46:25,622][00197] Num frames 3000...
1445
+ [2024-09-21 13:46:25,755][00197] Num frames 3100...
1446
+ [2024-09-21 13:46:25,883][00197] Num frames 3200...
1447
+ [2024-09-21 13:46:26,016][00197] Num frames 3300...
1448
+ [2024-09-21 13:46:26,144][00197] Num frames 3400...
1449
+ [2024-09-21 13:46:26,277][00197] Num frames 3500...
1450
+ [2024-09-21 13:46:26,361][00197] Avg episode rewards: #0: 23.400, true rewards: #0: 11.733
1451
+ [2024-09-21 13:46:26,363][00197] Avg episode reward: 23.400, avg true_objective: 11.733
1452
+ [2024-09-21 13:46:26,470][00197] Num frames 3600...
1453
+ [2024-09-21 13:46:26,596][00197] Num frames 3700...
1454
+ [2024-09-21 13:46:26,727][00197] Num frames 3800...
1455
+ [2024-09-21 13:46:26,852][00197] Num frames 3900...
1456
+ [2024-09-21 13:46:27,015][00197] Avg episode rewards: #0: 20.183, true rewards: #0: 9.932
1457
+ [2024-09-21 13:46:27,016][00197] Avg episode reward: 20.183, avg true_objective: 9.932
1458
+ [2024-09-21 13:46:27,058][00197] Num frames 4000...
1459
+ [2024-09-21 13:46:27,180][00197] Num frames 4100...
1460
+ [2024-09-21 13:46:27,309][00197] Num frames 4200...
1461
+ [2024-09-21 13:46:27,435][00197] Num frames 4300...
1462
+ [2024-09-21 13:46:27,563][00197] Num frames 4400...
1463
+ [2024-09-21 13:46:27,697][00197] Num frames 4500...
1464
+ [2024-09-21 13:46:27,825][00197] Num frames 4600...
1465
+ [2024-09-21 13:46:27,966][00197] Num frames 4700...
1466
+ [2024-09-21 13:46:28,095][00197] Num frames 4800...
1467
+ [2024-09-21 13:46:28,246][00197] Num frames 4900...
1468
+ [2024-09-21 13:46:28,356][00197] Avg episode rewards: #0: 21.274, true rewards: #0: 9.874
1469
+ [2024-09-21 13:46:28,357][00197] Avg episode reward: 21.274, avg true_objective: 9.874
1470
+ [2024-09-21 13:46:28,444][00197] Num frames 5000...
1471
+ [2024-09-21 13:46:28,571][00197] Num frames 5100...
1472
+ [2024-09-21 13:46:28,712][00197] Num frames 5200...
1473
+ [2024-09-21 13:46:28,844][00197] Num frames 5300...
1474
+ [2024-09-21 13:46:28,976][00197] Num frames 5400...
1475
+ [2024-09-21 13:46:29,116][00197] Num frames 5500...
1476
+ [2024-09-21 13:46:29,241][00197] Num frames 5600...
1477
+ [2024-09-21 13:46:29,371][00197] Num frames 5700...
1478
+ [2024-09-21 13:46:29,502][00197] Num frames 5800...
1479
+ [2024-09-21 13:46:29,628][00197] Num frames 5900...
1480
+ [2024-09-21 13:46:29,760][00197] Num frames 6000...
1481
+ [2024-09-21 13:46:29,891][00197] Num frames 6100...
1482
+ [2024-09-21 13:46:30,069][00197] Avg episode rewards: #0: 23.154, true rewards: #0: 10.320
1483
+ [2024-09-21 13:46:30,071][00197] Avg episode reward: 23.154, avg true_objective: 10.320
1484
+ [2024-09-21 13:46:30,086][00197] Num frames 6200...
1485
+ [2024-09-21 13:46:30,217][00197] Num frames 6300...
1486
+ [2024-09-21 13:46:30,349][00197] Num frames 6400...
1487
+ [2024-09-21 13:46:30,485][00197] Num frames 6500...
1488
+ [2024-09-21 13:46:30,608][00197] Num frames 6600...
1489
+ [2024-09-21 13:46:30,757][00197] Avg episode rewards: #0: 20.954, true rewards: #0: 9.526
1490
+ [2024-09-21 13:46:30,758][00197] Avg episode reward: 20.954, avg true_objective: 9.526
1491
+ [2024-09-21 13:46:30,803][00197] Num frames 6700...
1492
+ [2024-09-21 13:46:30,929][00197] Num frames 6800...
1493
+ [2024-09-21 13:46:31,072][00197] Num frames 6900...
1494
+ [2024-09-21 13:46:31,196][00197] Num frames 7000...
1495
+ [2024-09-21 13:46:31,328][00197] Num frames 7100...
1496
+ [2024-09-21 13:46:31,458][00197] Num frames 7200...
1497
+ [2024-09-21 13:46:31,608][00197] Avg episode rewards: #0: 20.220, true rewards: #0: 9.095
1498
+ [2024-09-21 13:46:31,610][00197] Avg episode reward: 20.220, avg true_objective: 9.095
1499
+ [2024-09-21 13:46:31,643][00197] Num frames 7300...
1500
+ [2024-09-21 13:46:31,777][00197] Num frames 7400...
1501
+ [2024-09-21 13:46:31,910][00197] Num frames 7500...
1502
+ [2024-09-21 13:46:32,041][00197] Num frames 7600...
1503
+ [2024-09-21 13:46:32,182][00197] Num frames 7700...
1504
+ [2024-09-21 13:46:32,270][00197] Avg episode rewards: #0: 18.805, true rewards: #0: 8.582
1505
+ [2024-09-21 13:46:32,271][00197] Avg episode reward: 18.805, avg true_objective: 8.582
1506
+ [2024-09-21 13:46:32,372][00197] Num frames 7800...
1507
+ [2024-09-21 13:46:32,511][00197] Num frames 7900...
1508
+ [2024-09-21 13:46:32,646][00197] Num frames 8000...
1509
+ [2024-09-21 13:46:32,793][00197] Num frames 8100...
1510
+ [2024-09-21 13:46:32,889][00197] Avg episode rewards: #0: 17.530, true rewards: #0: 8.130
1511
+ [2024-09-21 13:46:32,891][00197] Avg episode reward: 17.530, avg true_objective: 8.130
1512
+ [2024-09-21 13:47:25,447][00197] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
1513
+ [2024-09-21 13:50:04,195][00197] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
1514
+ [2024-09-21 13:50:04,196][00197] Overriding arg 'num_workers' with value 1 passed from command line
1515
+ [2024-09-21 13:50:04,198][00197] Adding new argument 'no_render'=True that is not in the saved config file!
1516
+ [2024-09-21 13:50:04,200][00197] Adding new argument 'save_video'=True that is not in the saved config file!
1517
+ [2024-09-21 13:50:04,201][00197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1518
+ [2024-09-21 13:50:04,203][00197] Adding new argument 'video_name'=None that is not in the saved config file!
1519
+ [2024-09-21 13:50:04,206][00197] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
1520
+ [2024-09-21 13:50:04,207][00197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1521
+ [2024-09-21 13:50:04,209][00197] Adding new argument 'push_to_hub'=True that is not in the saved config file!
1522
+ [2024-09-21 13:50:04,211][00197] Adding new argument 'hf_repository'='yhyeo0202/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
1523
+ [2024-09-21 13:50:04,213][00197] Adding new argument 'policy_index'=0 that is not in the saved config file!
1524
+ [2024-09-21 13:50:04,215][00197] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1525
+ [2024-09-21 13:50:04,217][00197] Adding new argument 'train_script'=None that is not in the saved config file!
1526
+ [2024-09-21 13:50:04,218][00197] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1527
+ [2024-09-21 13:50:04,219][00197] Using frameskip 1 and render_action_repeat=4 for evaluation
1528
+ [2024-09-21 13:50:04,236][00197] RunningMeanStd input shape: (3, 72, 128)
1529
+ [2024-09-21 13:50:04,238][00197] RunningMeanStd input shape: (1,)
1530
+ [2024-09-21 13:50:04,251][00197] ConvEncoder: input_channels=3
1531
+ [2024-09-21 13:50:04,291][00197] Conv encoder output size: 512
1532
+ [2024-09-21 13:50:04,293][00197] Policy head output size: 512
1533
+ [2024-09-21 13:50:04,315][00197] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
1534
+ [2024-09-21 13:50:04,862][00197] Num frames 100...
1535
+ [2024-09-21 13:50:04,984][00197] Num frames 200...
1536
+ [2024-09-21 13:50:05,111][00197] Num frames 300...
1537
+ [2024-09-21 13:50:05,241][00197] Num frames 400...
1538
+ [2024-09-21 13:50:05,401][00197] Avg episode rewards: #0: 8.750, true rewards: #0: 4.750
1539
+ [2024-09-21 13:50:05,403][00197] Avg episode reward: 8.750, avg true_objective: 4.750
1540
+ [2024-09-21 13:50:05,437][00197] Num frames 500...
1541
+ [2024-09-21 13:50:05,566][00197] Num frames 600...
1542
+ [2024-09-21 13:50:05,701][00197] Num frames 700...
1543
+ [2024-09-21 13:50:05,826][00197] Num frames 800...
1544
+ [2024-09-21 13:50:05,949][00197] Num frames 900...
1545
+ [2024-09-21 13:50:06,075][00197] Num frames 1000...
1546
+ [2024-09-21 13:50:06,204][00197] Num frames 1100...
1547
+ [2024-09-21 13:50:06,345][00197] Num frames 1200...
1548
+ [2024-09-21 13:50:06,485][00197] Num frames 1300...
1549
+ [2024-09-21 13:50:06,613][00197] Num frames 1400...
1550
+ [2024-09-21 13:50:06,741][00197] Avg episode rewards: #0: 16.760, true rewards: #0: 7.260
1551
+ [2024-09-21 13:50:06,744][00197] Avg episode reward: 16.760, avg true_objective: 7.260
1552
+ [2024-09-21 13:50:06,806][00197] Num frames 1500...
1553
+ [2024-09-21 13:50:06,935][00197] Num frames 1600...
1554
+ [2024-09-21 13:50:07,066][00197] Num frames 1700...
1555
+ [2024-09-21 13:50:07,198][00197] Num frames 1800...
1556
+ [2024-09-21 13:50:07,330][00197] Num frames 1900...
1557
+ [2024-09-21 13:50:07,464][00197] Num frames 2000...
1558
+ [2024-09-21 13:50:07,600][00197] Num frames 2100...
1559
+ [2024-09-21 13:50:07,732][00197] Num frames 2200...
1560
+ [2024-09-21 13:50:07,858][00197] Avg episode rewards: #0: 16.507, true rewards: #0: 7.507
1561
+ [2024-09-21 13:50:07,861][00197] Avg episode reward: 16.507, avg true_objective: 7.507
1562
+ [2024-09-21 13:50:07,925][00197] Num frames 2300...
1563
+ [2024-09-21 13:50:08,049][00197] Num frames 2400...
1564
+ [2024-09-21 13:50:08,181][00197] Num frames 2500...
1565
+ [2024-09-21 13:50:08,315][00197] Num frames 2600...
1566
+ [2024-09-21 13:50:08,467][00197] Num frames 2700...
1567
+ [2024-09-21 13:50:08,603][00197] Num frames 2800...
1568
+ [2024-09-21 13:50:08,753][00197] Num frames 2900...
1569
+ [2024-09-21 13:50:08,888][00197] Num frames 3000...
1570
+ [2024-09-21 13:50:09,028][00197] Num frames 3100...
1571
+ [2024-09-21 13:50:09,181][00197] Num frames 3200...
1572
+ [2024-09-21 13:50:09,374][00197] Num frames 3300...
1573
+ [2024-09-21 13:50:09,551][00197] Num frames 3400...
1574
+ [2024-09-21 13:50:09,736][00197] Num frames 3500...
1575
+ [2024-09-21 13:50:09,851][00197] Avg episode rewards: #0: 20.080, true rewards: #0: 8.830
1576
+ [2024-09-21 13:50:09,853][00197] Avg episode reward: 20.080, avg true_objective: 8.830
1577
+ [2024-09-21 13:50:09,974][00197] Num frames 3600...
1578
+ [2024-09-21 13:50:10,156][00197] Num frames 3700...
1579
+ [2024-09-21 13:50:10,333][00197] Num frames 3800...
1580
+ [2024-09-21 13:50:10,530][00197] Num frames 3900...
1581
+ [2024-09-21 13:50:10,711][00197] Num frames 4000...
1582
+ [2024-09-21 13:50:10,891][00197] Num frames 4100...
1583
+ [2024-09-21 13:50:11,111][00197] Num frames 4200...
1584
+ [2024-09-21 13:50:11,181][00197] Avg episode rewards: #0: 19.008, true rewards: #0: 8.408
1585
+ [2024-09-21 13:50:11,184][00197] Avg episode reward: 19.008, avg true_objective: 8.408
1586
+ [2024-09-21 13:50:11,381][00197] Num frames 4300...
1587
+ [2024-09-21 13:50:11,596][00197] Num frames 4400...
1588
+ [2024-09-21 13:50:11,795][00197] Num frames 4500...
1589
+ [2024-09-21 13:50:12,009][00197] Num frames 4600...
1590
+ [2024-09-21 13:50:12,257][00197] Num frames 4700...
1591
+ [2024-09-21 13:50:12,481][00197] Num frames 4800...
1592
+ [2024-09-21 13:50:12,658][00197] Num frames 4900...
1593
+ [2024-09-21 13:50:12,837][00197] Num frames 5000...
1594
+ [2024-09-21 13:50:13,010][00197] Num frames 5100...
1595
+ [2024-09-21 13:50:13,199][00197] Num frames 5200...
1596
+ [2024-09-21 13:50:13,387][00197] Num frames 5300...
1597
+ [2024-09-21 13:50:13,584][00197] Num frames 5400...
1598
+ [2024-09-21 13:50:13,776][00197] Num frames 5500...
1599
+ [2024-09-21 13:50:13,960][00197] Num frames 5600...
1600
+ [2024-09-21 13:50:14,149][00197] Num frames 5700...
1601
+ [2024-09-21 13:50:14,335][00197] Num frames 5800...
1602
+ [2024-09-21 13:50:14,527][00197] Num frames 5900...
1603
+ [2024-09-21 13:50:14,634][00197] Avg episode rewards: #0: 23.887, true rewards: #0: 9.887
1604
+ [2024-09-21 13:50:14,636][00197] Avg episode reward: 23.887, avg true_objective: 9.887
1605
+ [2024-09-21 13:50:14,734][00197] Num frames 6000...
1606
+ [2024-09-21 13:50:14,875][00197] Num frames 6100...
1607
+ [2024-09-21 13:50:14,998][00197] Num frames 6200...
1608
+ [2024-09-21 13:50:15,123][00197] Num frames 6300...
1609
+ [2024-09-21 13:50:15,289][00197] Num frames 6400...
1610
+ [2024-09-21 13:50:15,423][00197] Num frames 6500...
1611
+ [2024-09-21 13:50:15,547][00197] Num frames 6600...
1612
+ [2024-09-21 13:50:15,686][00197] Num frames 6700...
1613
+ [2024-09-21 13:50:15,822][00197] Num frames 6800...
1614
+ [2024-09-21 13:50:15,949][00197] Num frames 6900...
1615
+ [2024-09-21 13:50:16,075][00197] Num frames 7000...
1616
+ [2024-09-21 13:50:16,201][00197] Num frames 7100...
1617
+ [2024-09-21 13:50:16,333][00197] Num frames 7200...
1618
+ [2024-09-21 13:50:16,456][00197] Num frames 7300...
1619
+ [2024-09-21 13:50:16,587][00197] Num frames 7400...
1620
+ [2024-09-21 13:50:16,718][00197] Num frames 7500...
1621
+ [2024-09-21 13:50:16,854][00197] Num frames 7600...
1622
+ [2024-09-21 13:50:16,947][00197] Avg episode rewards: #0: 25.897, true rewards: #0: 10.897
1623
+ [2024-09-21 13:50:16,952][00197] Avg episode reward: 25.897, avg true_objective: 10.897
1624
+ [2024-09-21 13:50:17,043][00197] Num frames 7700...
1625
+ [2024-09-21 13:50:17,171][00197] Num frames 7800...
1626
+ [2024-09-21 13:50:17,300][00197] Num frames 7900...
1627
+ [2024-09-21 13:50:17,427][00197] Num frames 8000...
1628
+ [2024-09-21 13:50:17,559][00197] Num frames 8100...
1629
+ [2024-09-21 13:50:17,709][00197] Num frames 8200...
1630
+ [2024-09-21 13:50:17,793][00197] Avg episode rewards: #0: 24.149, true rewards: #0: 10.274
1631
+ [2024-09-21 13:50:17,796][00197] Avg episode reward: 24.149, avg true_objective: 10.274
1632
+ [2024-09-21 13:50:17,920][00197] Num frames 8300...
1633
+ [2024-09-21 13:50:18,059][00197] Num frames 8400...
1634
+ [2024-09-21 13:50:18,204][00197] Num frames 8500...
1635
+ [2024-09-21 13:50:18,335][00197] Num frames 8600...
1636
+ [2024-09-21 13:50:18,456][00197] Num frames 8700...
1637
+ [2024-09-21 13:50:18,586][00197] Num frames 8800...
1638
+ [2024-09-21 13:50:18,728][00197] Num frames 8900...
1639
+ [2024-09-21 13:50:18,890][00197] Avg episode rewards: #0: 23.208, true rewards: #0: 9.986
1640
+ [2024-09-21 13:50:18,892][00197] Avg episode reward: 23.208, avg true_objective: 9.986
1641
+ [2024-09-21 13:50:18,915][00197] Num frames 9000...
1642
+ [2024-09-21 13:50:19,040][00197] Num frames 9100...
1643
+ [2024-09-21 13:50:19,161][00197] Num frames 9200...
1644
+ [2024-09-21 13:50:19,293][00197] Num frames 9300...
1645
+ [2024-09-21 13:50:19,422][00197] Num frames 9400...
1646
+ [2024-09-21 13:50:19,552][00197] Num frames 9500...
1647
+ [2024-09-21 13:50:19,686][00197] Num frames 9600...
1648
+ [2024-09-21 13:50:19,853][00197] Avg episode rewards: #0: 22.091, true rewards: #0: 9.691
1649
+ [2024-09-21 13:50:19,855][00197] Avg episode reward: 22.091, avg true_objective: 9.691
1650
+ [2024-09-21 13:51:21,987][00197] Replay video saved to /content/train_dir/default_experiment/replay.mp4!