usamabuttar
commited on
Commit
•
2637f1c
1
Parent(s):
88a2333
Upload folder using huggingface_hub
Browse files- README.md +1 -1
- replay.mp4 +2 -2
- 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.
|
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:
|
3 |
-
size
|
|
|
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!
|