File size: 26,654 Bytes
c526692 3bb9242 c526692 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 |
[2023-02-22 18:52:22,088][18494] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-22 18:52:22,094][18494] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-22 18:52:22,455][18508] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-22 18:52:22,468][18508] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-22 18:52:22,636][18513] Worker 4 uses CPU cores [0] [2023-02-22 18:52:22,646][18516] Worker 6 uses CPU cores [0] [2023-02-22 18:52:22,654][18510] Worker 2 uses CPU cores [0] [2023-02-22 18:52:22,720][18512] Worker 3 uses CPU cores [1] [2023-02-22 18:52:22,733][18509] Worker 0 uses CPU cores [0] [2023-02-22 18:52:22,750][18515] Worker 7 uses CPU cores [1] [2023-02-22 18:52:22,921][18511] Worker 1 uses CPU cores [1] [2023-02-22 18:52:22,924][18514] Worker 5 uses CPU cores [1] [2023-02-22 18:52:23,261][18508] Num visible devices: 1 [2023-02-22 18:52:23,262][18494] Num visible devices: 1 [2023-02-22 18:52:23,263][18494] Starting seed is not provided [2023-02-22 18:52:23,263][18494] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-22 18:52:23,264][18494] Initializing actor-critic model on device cuda:0 [2023-02-22 18:52:23,265][18494] RunningMeanStd input shape: (3, 72, 128) [2023-02-22 18:52:23,266][18494] RunningMeanStd input shape: (1,) [2023-02-22 18:52:23,286][18494] ConvEncoder: input_channels=3 [2023-02-22 18:52:23,468][18494] Conv encoder output size: 512 [2023-02-22 18:52:23,469][18494] Policy head output size: 512 [2023-02-22 18:52:23,492][18494] Created Actor Critic model with architecture: [2023-02-22 18:52:23,493][18494] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-02-22 18:52:25,754][18494] Using optimizer <class 'torch.optim.adam.Adam'> [2023-02-22 18:52:25,755][18494] No checkpoints found [2023-02-22 18:52:25,756][18494] Did not load from checkpoint, starting from scratch! [2023-02-22 18:52:25,756][18494] Initialized policy 0 weights for model version 0 [2023-02-22 18:52:25,760][18494] LearnerWorker_p0 finished initialization! [2023-02-22 18:52:25,761][18494] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-22 18:52:25,974][18508] RunningMeanStd input shape: (3, 72, 128) [2023-02-22 18:52:25,975][18508] RunningMeanStd input shape: (1,) [2023-02-22 18:52:25,991][18508] ConvEncoder: input_channels=3 [2023-02-22 18:52:26,091][18508] Conv encoder output size: 512 [2023-02-22 18:52:26,091][18508] Policy head output size: 512 [2023-02-22 18:52:28,437][18509] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,444][18510] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,475][18511] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,474][18516] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,477][18515] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,486][18514] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,489][18512] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:28,491][18513] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-22 18:52:29,641][18511] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,642][18512] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,643][18514] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,881][18509] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,876][18513] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,885][18510] Decorrelating experience for 0 frames... [2023-02-22 18:52:29,901][18516] Decorrelating experience for 0 frames... [2023-02-22 18:52:30,514][18514] Decorrelating experience for 32 frames... [2023-02-22 18:52:30,560][18515] Decorrelating experience for 0 frames... [2023-02-22 18:52:30,890][18511] Decorrelating experience for 32 frames... [2023-02-22 18:52:30,982][18509] Decorrelating experience for 32 frames... [2023-02-22 18:52:30,985][18513] Decorrelating experience for 32 frames... [2023-02-22 18:52:30,994][18510] Decorrelating experience for 32 frames... [2023-02-22 18:52:31,638][18515] Decorrelating experience for 32 frames... [2023-02-22 18:52:31,764][18516] Decorrelating experience for 32 frames... [2023-02-22 18:52:32,185][18510] Decorrelating experience for 64 frames... [2023-02-22 18:52:32,191][18513] Decorrelating experience for 64 frames... [2023-02-22 18:52:32,387][18514] Decorrelating experience for 64 frames... [2023-02-22 18:52:32,394][18512] Decorrelating experience for 32 frames... [2023-02-22 18:52:32,402][18511] Decorrelating experience for 64 frames... [2023-02-22 18:52:33,107][18515] Decorrelating experience for 64 frames... [2023-02-22 18:52:33,500][18514] Decorrelating experience for 96 frames... [2023-02-22 18:52:33,509][18510] Decorrelating experience for 96 frames... [2023-02-22 18:52:33,513][18513] Decorrelating experience for 96 frames... [2023-02-22 18:52:33,697][18512] Decorrelating experience for 64 frames... [2023-02-22 18:52:34,207][18516] Decorrelating experience for 64 frames... [2023-02-22 18:52:34,214][18509] Decorrelating experience for 64 frames... [2023-02-22 18:52:34,623][18515] Decorrelating experience for 96 frames... [2023-02-22 18:52:34,629][18511] Decorrelating experience for 96 frames... [2023-02-22 18:52:35,339][18512] Decorrelating experience for 96 frames... [2023-02-22 18:52:36,064][18516] Decorrelating experience for 96 frames... [2023-02-22 18:52:36,085][18509] Decorrelating experience for 96 frames... [2023-02-22 18:52:42,053][18494] Signal inference workers to stop experience collection... [2023-02-22 18:52:42,116][18508] InferenceWorker_p0-w0: stopping experience collection [2023-02-22 18:52:44,184][18494] Signal inference workers to resume experience collection... [2023-02-22 18:52:44,187][18508] InferenceWorker_p0-w0: resuming experience collection [2023-02-22 18:52:51,922][18508] Updated weights for policy 0, policy_version 10 (0.0338) [2023-02-22 18:53:03,897][18508] Updated weights for policy 0, policy_version 20 (0.0021) [2023-02-22 18:53:10,170][18494] Saving new best policy, reward=4.191! [2023-02-22 18:53:12,948][18508] Updated weights for policy 0, policy_version 30 (0.0014) [2023-02-22 18:53:15,156][18494] Saving new best policy, reward=4.205! [2023-02-22 18:53:24,545][18508] Updated weights for policy 0, policy_version 40 (0.0025) [2023-02-22 18:53:25,231][18494] Saving new best policy, reward=4.251! [2023-02-22 18:53:30,169][18494] Saving new best policy, reward=4.532! [2023-02-22 18:53:33,956][18508] Updated weights for policy 0, policy_version 50 (0.0026) [2023-02-22 18:53:45,138][18508] Updated weights for policy 0, policy_version 60 (0.0016) [2023-02-22 18:53:50,186][18494] Saving new best policy, reward=4.588! [2023-02-22 18:53:54,603][18508] Updated weights for policy 0, policy_version 70 (0.0023) [2023-02-22 18:54:05,216][18494] Saving new best policy, reward=4.629! [2023-02-22 18:54:05,221][18508] Updated weights for policy 0, policy_version 80 (0.0030) [2023-02-22 18:54:10,165][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000083_339968.pth... [2023-02-22 18:54:19,873][18508] Updated weights for policy 0, policy_version 90 (0.0027) [2023-02-22 18:54:25,154][18494] Saving new best policy, reward=4.694! [2023-02-22 18:54:29,311][18508] Updated weights for policy 0, policy_version 100 (0.0017) [2023-02-22 18:54:30,189][18494] Saving new best policy, reward=4.702! [2023-02-22 18:54:40,931][18508] Updated weights for policy 0, policy_version 110 (0.0017) [2023-02-22 18:54:45,156][18494] Saving new best policy, reward=4.806! [2023-02-22 18:54:49,636][18508] Updated weights for policy 0, policy_version 120 (0.0030) [2023-02-22 18:55:00,261][18494] Saving new best policy, reward=4.984! [2023-02-22 18:55:01,559][18508] Updated weights for policy 0, policy_version 130 (0.0013) [2023-02-22 18:55:10,154][18508] Updated weights for policy 0, policy_version 140 (0.0011) [2023-02-22 18:55:20,171][18494] Saving new best policy, reward=5.100! [2023-02-22 18:55:21,905][18508] Updated weights for policy 0, policy_version 150 (0.0019) [2023-02-22 18:55:25,160][18494] Saving new best policy, reward=5.200! [2023-02-22 18:55:30,400][18508] Updated weights for policy 0, policy_version 160 (0.0013) [2023-02-22 18:55:42,165][18508] Updated weights for policy 0, policy_version 170 (0.0020) [2023-02-22 18:55:50,168][18494] Saving new best policy, reward=5.430! [2023-02-22 18:55:50,642][18508] Updated weights for policy 0, policy_version 180 (0.0018) [2023-02-22 18:55:55,162][18494] Saving new best policy, reward=5.935! [2023-02-22 18:56:02,727][18508] Updated weights for policy 0, policy_version 190 (0.0014) [2023-02-22 18:56:05,160][18494] Saving new best policy, reward=5.956! [2023-02-22 18:56:10,166][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000198_811008.pth... [2023-02-22 18:56:10,313][18494] Saving new best policy, reward=6.201! [2023-02-22 18:56:11,589][18508] Updated weights for policy 0, policy_version 200 (0.0015) [2023-02-22 18:56:15,158][18494] Saving new best policy, reward=6.805! [2023-02-22 18:56:20,171][18494] Saving new best policy, reward=6.821! [2023-02-22 18:56:23,530][18508] Updated weights for policy 0, policy_version 210 (0.0012) [2023-02-22 18:56:25,161][18494] Saving new best policy, reward=6.914! [2023-02-22 18:56:30,224][18494] Saving new best policy, reward=6.963! [2023-02-22 18:56:32,783][18508] Updated weights for policy 0, policy_version 220 (0.0028) [2023-02-22 18:56:35,160][18494] Saving new best policy, reward=7.309! [2023-02-22 18:56:43,943][18508] Updated weights for policy 0, policy_version 230 (0.0021) [2023-02-22 18:56:53,708][18508] Updated weights for policy 0, policy_version 240 (0.0012) [2023-02-22 18:57:04,323][18508] Updated weights for policy 0, policy_version 250 (0.0014) [2023-02-22 18:57:14,724][18508] Updated weights for policy 0, policy_version 260 (0.0012) [2023-02-22 18:57:20,167][18494] Saving new best policy, reward=7.435! [2023-02-22 18:57:25,048][18508] Updated weights for policy 0, policy_version 270 (0.0017) [2023-02-22 18:57:35,159][18494] Saving new best policy, reward=7.552! [2023-02-22 18:57:35,781][18508] Updated weights for policy 0, policy_version 280 (0.0016) [2023-02-22 18:57:40,169][18494] Saving new best policy, reward=7.882! [2023-02-22 18:57:45,158][18494] Saving new best policy, reward=8.241! [2023-02-22 18:57:45,586][18508] Updated weights for policy 0, policy_version 290 (0.0015) [2023-02-22 18:57:55,163][18494] Saving new best policy, reward=8.245! [2023-02-22 18:57:56,872][18508] Updated weights for policy 0, policy_version 300 (0.0025) [2023-02-22 18:58:00,167][18494] Saving new best policy, reward=9.512! [2023-02-22 18:58:05,157][18494] Saving new best policy, reward=10.187! [2023-02-22 18:58:06,102][18508] Updated weights for policy 0, policy_version 310 (0.0013) [2023-02-22 18:58:10,176][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000314_1286144.pth... [2023-02-22 18:58:10,377][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000083_339968.pth [2023-02-22 18:58:10,391][18494] Saving new best policy, reward=11.235! [2023-02-22 18:58:15,154][18494] Saving new best policy, reward=12.271! [2023-02-22 18:58:18,369][18508] Updated weights for policy 0, policy_version 320 (0.0032) [2023-02-22 18:58:20,164][18494] Saving new best policy, reward=12.977! [2023-02-22 18:58:25,159][18494] Saving new best policy, reward=13.710! [2023-02-22 18:58:26,845][18508] Updated weights for policy 0, policy_version 330 (0.0013) [2023-02-22 18:58:39,520][18508] Updated weights for policy 0, policy_version 340 (0.0019) [2023-02-22 18:58:52,509][18508] Updated weights for policy 0, policy_version 350 (0.0018) [2023-02-22 18:58:55,199][18494] Saving new best policy, reward=13.881! [2023-02-22 18:59:00,167][18494] Saving new best policy, reward=15.240! [2023-02-22 18:59:02,958][18508] Updated weights for policy 0, policy_version 360 (0.0014) [2023-02-22 18:59:10,168][18494] Saving new best policy, reward=15.378! [2023-02-22 18:59:13,687][18508] Updated weights for policy 0, policy_version 370 (0.0011) [2023-02-22 18:59:15,167][18494] Saving new best policy, reward=16.206! [2023-02-22 18:59:23,567][18508] Updated weights for policy 0, policy_version 380 (0.0019) [2023-02-22 18:59:25,162][18494] Saving new best policy, reward=16.728! [2023-02-22 18:59:30,168][18494] Saving new best policy, reward=17.859! [2023-02-22 18:59:34,808][18508] Updated weights for policy 0, policy_version 390 (0.0012) [2023-02-22 18:59:40,161][18494] Saving new best policy, reward=18.218! [2023-02-22 18:59:44,145][18508] Updated weights for policy 0, policy_version 400 (0.0021) [2023-02-22 18:59:45,155][18494] Saving new best policy, reward=18.396! [2023-02-22 18:59:50,170][18494] Saving new best policy, reward=19.251! [2023-02-22 18:59:55,604][18508] Updated weights for policy 0, policy_version 410 (0.0013) [2023-02-22 19:00:04,352][18508] Updated weights for policy 0, policy_version 420 (0.0011) [2023-02-22 19:00:10,162][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000425_1740800.pth... [2023-02-22 19:00:10,307][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000198_811008.pth [2023-02-22 19:00:16,510][18508] Updated weights for policy 0, policy_version 430 (0.0016) [2023-02-22 19:00:20,169][18494] Saving new best policy, reward=19.433! [2023-02-22 19:00:24,918][18508] Updated weights for policy 0, policy_version 440 (0.0023) [2023-02-22 19:00:25,159][18494] Saving new best policy, reward=19.548! [2023-02-22 19:00:36,903][18508] Updated weights for policy 0, policy_version 450 (0.0011) [2023-02-22 19:00:45,179][18508] Updated weights for policy 0, policy_version 460 (0.0019) [2023-02-22 19:00:57,269][18508] Updated weights for policy 0, policy_version 470 (0.0012) [2023-02-22 19:01:05,633][18508] Updated weights for policy 0, policy_version 480 (0.0013) [2023-02-22 19:01:17,487][18508] Updated weights for policy 0, policy_version 490 (0.0023) [2023-02-22 19:01:25,180][18494] Saving new best policy, reward=20.348! [2023-02-22 19:01:26,585][18508] Updated weights for policy 0, policy_version 500 (0.0016) [2023-02-22 19:01:30,170][18494] Saving new best policy, reward=20.421! [2023-02-22 19:01:37,786][18508] Updated weights for policy 0, policy_version 510 (0.0016) [2023-02-22 19:01:45,167][18494] Saving new best policy, reward=20.458! [2023-02-22 19:01:47,346][18508] Updated weights for policy 0, policy_version 520 (0.0030) [2023-02-22 19:01:50,193][18494] Saving new best policy, reward=21.617! [2023-02-22 19:01:55,159][18494] Saving new best policy, reward=22.472! [2023-02-22 19:01:58,324][18508] Updated weights for policy 0, policy_version 530 (0.0018) [2023-02-22 19:02:00,170][18494] Saving new best policy, reward=22.824! [2023-02-22 19:02:08,289][18508] Updated weights for policy 0, policy_version 540 (0.0011) [2023-02-22 19:02:10,171][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000541_2215936.pth... [2023-02-22 19:02:10,309][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000314_1286144.pth [2023-02-22 19:02:18,832][18508] Updated weights for policy 0, policy_version 550 (0.0028) [2023-02-22 19:02:29,136][18508] Updated weights for policy 0, policy_version 560 (0.0015) [2023-02-22 19:02:38,966][18508] Updated weights for policy 0, policy_version 570 (0.0027) [2023-02-22 19:02:50,118][18508] Updated weights for policy 0, policy_version 580 (0.0019) [2023-02-22 19:02:59,465][18508] Updated weights for policy 0, policy_version 590 (0.0014) [2023-02-22 19:03:11,008][18508] Updated weights for policy 0, policy_version 600 (0.0013) [2023-02-22 19:03:23,769][18508] Updated weights for policy 0, policy_version 610 (0.0029) [2023-02-22 19:03:35,094][18508] Updated weights for policy 0, policy_version 620 (0.0034) [2023-02-22 19:03:44,110][18508] Updated weights for policy 0, policy_version 630 (0.0026) [2023-02-22 19:03:55,449][18508] Updated weights for policy 0, policy_version 640 (0.0021) [2023-02-22 19:04:04,961][18508] Updated weights for policy 0, policy_version 650 (0.0022) [2023-02-22 19:04:10,173][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000653_2674688.pth... [2023-02-22 19:04:10,350][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000425_1740800.pth [2023-02-22 19:04:15,773][18508] Updated weights for policy 0, policy_version 660 (0.0016) [2023-02-22 19:04:25,669][18508] Updated weights for policy 0, policy_version 670 (0.0011) [2023-02-22 19:04:36,111][18508] Updated weights for policy 0, policy_version 680 (0.0020) [2023-02-22 19:04:47,035][18508] Updated weights for policy 0, policy_version 690 (0.0032) [2023-02-22 19:04:55,222][18494] Saving new best policy, reward=23.394! [2023-02-22 19:04:56,779][18508] Updated weights for policy 0, policy_version 700 (0.0015) [2023-02-22 19:05:08,006][18508] Updated weights for policy 0, policy_version 710 (0.0013) [2023-02-22 19:05:17,384][18508] Updated weights for policy 0, policy_version 720 (0.0020) [2023-02-22 19:05:28,657][18508] Updated weights for policy 0, policy_version 730 (0.0022) [2023-02-22 19:05:37,495][18508] Updated weights for policy 0, policy_version 740 (0.0036) [2023-02-22 19:05:49,212][18508] Updated weights for policy 0, policy_version 750 (0.0015) [2023-02-22 19:05:57,872][18508] Updated weights for policy 0, policy_version 760 (0.0021) [2023-02-22 19:06:09,765][18508] Updated weights for policy 0, policy_version 770 (0.0044) [2023-02-22 19:06:10,168][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000770_3153920.pth... [2023-02-22 19:06:10,307][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000541_2215936.pth [2023-02-22 19:06:18,309][18508] Updated weights for policy 0, policy_version 780 (0.0015) [2023-02-22 19:06:30,077][18508] Updated weights for policy 0, policy_version 790 (0.0015) [2023-02-22 19:06:38,169][18508] Updated weights for policy 0, policy_version 800 (0.0018) [2023-02-22 19:06:45,158][18494] Saving new best policy, reward=24.124! [2023-02-22 19:06:50,166][18494] Saving new best policy, reward=24.920! [2023-02-22 19:06:50,533][18508] Updated weights for policy 0, policy_version 810 (0.0039) [2023-02-22 19:06:55,155][18494] Saving new best policy, reward=26.242! [2023-02-22 19:06:59,472][18508] Updated weights for policy 0, policy_version 820 (0.0015) [2023-02-22 19:07:10,964][18508] Updated weights for policy 0, policy_version 830 (0.0031) [2023-02-22 19:07:20,255][18508] Updated weights for policy 0, policy_version 840 (0.0026) [2023-02-22 19:07:31,400][18508] Updated weights for policy 0, policy_version 850 (0.0018) [2023-02-22 19:07:40,844][18508] Updated weights for policy 0, policy_version 860 (0.0014) [2023-02-22 19:07:50,165][18494] Saving new best policy, reward=26.314! [2023-02-22 19:07:55,359][18508] Updated weights for policy 0, policy_version 870 (0.0042) [2023-02-22 19:08:05,366][18508] Updated weights for policy 0, policy_version 880 (0.0017) [2023-02-22 19:08:10,176][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000883_3616768.pth... [2023-02-22 19:08:10,356][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000653_2674688.pth [2023-02-22 19:08:15,695][18508] Updated weights for policy 0, policy_version 890 (0.0013) [2023-02-22 19:08:26,420][18508] Updated weights for policy 0, policy_version 900 (0.0031) [2023-02-22 19:08:35,909][18508] Updated weights for policy 0, policy_version 910 (0.0037) [2023-02-22 19:08:46,932][18508] Updated weights for policy 0, policy_version 920 (0.0032) [2023-02-22 19:08:56,357][18508] Updated weights for policy 0, policy_version 930 (0.0014) [2023-02-22 19:09:07,688][18508] Updated weights for policy 0, policy_version 940 (0.0013) [2023-02-22 19:09:16,391][18508] Updated weights for policy 0, policy_version 950 (0.0011) [2023-02-22 19:09:28,579][18508] Updated weights for policy 0, policy_version 960 (0.0011) [2023-02-22 19:09:36,897][18508] Updated weights for policy 0, policy_version 970 (0.0014) [2023-02-22 19:09:48,991][18508] Updated weights for policy 0, policy_version 980 (0.0033) [2023-02-22 19:09:57,581][18508] Updated weights for policy 0, policy_version 990 (0.0011) [2023-02-22 19:10:09,423][18508] Updated weights for policy 0, policy_version 1000 (0.0026) [2023-02-22 19:10:10,165][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001001_4100096.pth... [2023-02-22 19:10:10,282][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000770_3153920.pth [2023-02-22 19:10:17,695][18508] Updated weights for policy 0, policy_version 1010 (0.0012) [2023-02-22 19:10:29,555][18508] Updated weights for policy 0, policy_version 1020 (0.0020) [2023-02-22 19:10:38,054][18508] Updated weights for policy 0, policy_version 1030 (0.0026) [2023-02-22 19:10:49,652][18508] Updated weights for policy 0, policy_version 1040 (0.0028) [2023-02-22 19:10:58,506][18508] Updated weights for policy 0, policy_version 1050 (0.0012) [2023-02-22 19:11:10,211][18508] Updated weights for policy 0, policy_version 1060 (0.0012) [2023-02-22 19:11:19,404][18508] Updated weights for policy 0, policy_version 1070 (0.0011) [2023-02-22 19:11:30,700][18508] Updated weights for policy 0, policy_version 1080 (0.0023) [2023-02-22 19:11:39,896][18508] Updated weights for policy 0, policy_version 1090 (0.0033) [2023-02-22 19:11:50,890][18508] Updated weights for policy 0, policy_version 1100 (0.0011) [2023-02-22 19:12:00,614][18508] Updated weights for policy 0, policy_version 1110 (0.0015) [2023-02-22 19:12:10,171][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001118_4579328.pth... [2023-02-22 19:12:10,311][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000883_3616768.pth [2023-02-22 19:12:12,804][18508] Updated weights for policy 0, policy_version 1120 (0.0020) [2023-02-22 19:12:26,550][18508] Updated weights for policy 0, policy_version 1130 (0.0018) [2023-02-22 19:12:35,018][18508] Updated weights for policy 0, policy_version 1140 (0.0018) [2023-02-22 19:12:46,742][18508] Updated weights for policy 0, policy_version 1150 (0.0021) [2023-02-22 19:12:55,110][18508] Updated weights for policy 0, policy_version 1160 (0.0018) [2023-02-22 19:13:07,263][18508] Updated weights for policy 0, policy_version 1170 (0.0016) [2023-02-22 19:13:15,160][18494] Saving new best policy, reward=26.727! [2023-02-22 19:13:15,694][18508] Updated weights for policy 0, policy_version 1180 (0.0014) [2023-02-22 19:13:27,579][18508] Updated weights for policy 0, policy_version 1190 (0.0021) [2023-02-22 19:13:36,030][18508] Updated weights for policy 0, policy_version 1200 (0.0028) [2023-02-22 19:13:47,959][18508] Updated weights for policy 0, policy_version 1210 (0.0020) [2023-02-22 19:13:56,937][18508] Updated weights for policy 0, policy_version 1220 (0.0017) [2023-02-22 19:13:59,627][18494] Stopping Batcher_0... [2023-02-22 19:13:59,629][18494] Loop batcher_evt_loop terminating... [2023-02-22 19:13:59,635][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth... [2023-02-22 19:13:59,669][18512] Stopping RolloutWorker_w3... [2023-02-22 19:13:59,686][18511] Stopping RolloutWorker_w1... [2023-02-22 19:13:59,691][18508] Weights refcount: 2 0 [2023-02-22 19:13:59,687][18511] Loop rollout_proc1_evt_loop terminating... [2023-02-22 19:13:59,682][18512] Loop rollout_proc3_evt_loop terminating... [2023-02-22 19:13:59,695][18508] Stopping InferenceWorker_p0-w0... [2023-02-22 19:13:59,700][18508] Loop inference_proc0-0_evt_loop terminating... [2023-02-22 19:13:59,714][18514] Stopping RolloutWorker_w5... [2023-02-22 19:13:59,715][18514] Loop rollout_proc5_evt_loop terminating... [2023-02-22 19:13:59,724][18515] Stopping RolloutWorker_w7... [2023-02-22 19:13:59,728][18515] Loop rollout_proc7_evt_loop terminating... [2023-02-22 19:13:59,832][18513] Stopping RolloutWorker_w4... [2023-02-22 19:13:59,833][18513] Loop rollout_proc4_evt_loop terminating... [2023-02-22 19:13:59,839][18509] Stopping RolloutWorker_w0... [2023-02-22 19:13:59,844][18494] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001001_4100096.pth [2023-02-22 19:13:59,862][18509] Loop rollout_proc0_evt_loop terminating... [2023-02-22 19:13:59,864][18494] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth... [2023-02-22 19:13:59,879][18510] Stopping RolloutWorker_w2... [2023-02-22 19:13:59,889][18510] Loop rollout_proc2_evt_loop terminating... [2023-02-22 19:13:59,900][18516] Stopping RolloutWorker_w6... [2023-02-22 19:13:59,913][18516] Loop rollout_proc6_evt_loop terminating... [2023-02-22 19:14:00,175][18494] Stopping LearnerWorker_p0... [2023-02-22 19:14:00,176][18494] Loop learner_proc0_evt_loop terminating... |