Upload folder using huggingface_hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.94 +/- 5.49
+      value: 6.43 +/- 1.43
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e20b33a42c48880b9ca59255da65bfa4b12c4aa479019e14330f37610158f1
-size 18942700
+oid sha256:7c2846299f6fafb81feed852f02a6a4c6c95525c15ccf9bdb42848a1dce510f9
+size 11960428

sf_log.txt

@@ -1121,3 +1121,110 @@ main_loop: 1150.4710
 [2024-07-24 19:33:15,594][02885] Avg episode rewards: #0: 22.838, true rewards: #0: 9.938
 [2024-07-24 19:33:15,596][02885] Avg episode reward: 22.838, avg true_objective: 9.938
 [2024-07-24 19:34:17,803][02885] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-07-24 19:34:23,227][02885] The model has been pushed to https://huggingface.co/dergky1/rl_course_vizdoom_health_gathering_supreme
+[2024-07-24 19:42:02,699][02885] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-24 19:42:02,704][02885] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-07-24 19:42:02,706][02885] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-07-24 19:42:02,707][02885] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-07-24 19:42:02,709][02885] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-24 19:42:02,714][02885] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-07-24 19:42:02,715][02885] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-07-24 19:42:02,717][02885] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-07-24 19:42:02,718][02885] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-07-24 19:42:02,720][02885] Adding new argument 'hf_repository'='dergky1/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-07-24 19:42:02,724][02885] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-07-24 19:42:02,725][02885] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-07-24 19:42:02,730][02885] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-07-24 19:42:02,734][02885] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-07-24 19:42:02,736][02885] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-07-24 19:42:02,779][02885] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-24 19:42:02,782][02885] RunningMeanStd input shape: (1,)
+[2024-07-24 19:42:02,801][02885] ConvEncoder: input_channels=3
+[2024-07-24 19:42:02,865][02885] Conv encoder output size: 512
+[2024-07-24 19:42:02,868][02885] Policy head output size: 512
+[2024-07-24 19:42:02,903][02885] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-07-24 19:42:03,570][02885] Num frames 100...
+[2024-07-24 19:42:03,752][02885] Num frames 200...
+[2024-07-24 19:42:03,929][02885] Num frames 300...
+[2024-07-24 19:42:04,126][02885] Num frames 400...
+[2024-07-24 19:42:04,273][02885] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-07-24 19:42:04,275][02885] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-07-24 19:42:04,372][02885] Num frames 500...
+[2024-07-24 19:42:04,563][02885] Num frames 600...
+[2024-07-24 19:42:04,751][02885] Num frames 700...
+[2024-07-24 19:42:04,957][02885] Num frames 800...
+[2024-07-24 19:42:05,188][02885] Num frames 900...
+[2024-07-24 19:42:05,343][02885] Num frames 1000...
+[2024-07-24 19:42:05,469][02885] Num frames 1100...
+[2024-07-24 19:42:05,593][02885] Num frames 1200...
+[2024-07-24 19:42:05,767][02885] Avg episode rewards: #0: 10.950, true rewards: #0: 6.450
+[2024-07-24 19:42:05,769][02885] Avg episode reward: 10.950, avg true_objective: 6.450
+[2024-07-24 19:42:05,785][02885] Num frames 1300...
+[2024-07-24 19:42:05,922][02885] Num frames 1400...
+[2024-07-24 19:42:06,060][02885] Num frames 1500...
+[2024-07-24 19:42:06,187][02885] Num frames 1600...
+[2024-07-24 19:42:06,315][02885] Num frames 1700...
+[2024-07-24 19:42:06,440][02885] Num frames 1800...
+[2024-07-24 19:42:06,578][02885] Avg episode rewards: #0: 10.553, true rewards: #0: 6.220
+[2024-07-24 19:42:06,580][02885] Avg episode reward: 10.553, avg true_objective: 6.220
+[2024-07-24 19:42:06,628][02885] Num frames 1900...
+[2024-07-24 19:42:06,757][02885] Num frames 2000...
+[2024-07-24 19:42:06,883][02885] Num frames 2100...
+[2024-07-24 19:42:07,024][02885] Num frames 2200...
+[2024-07-24 19:42:07,165][02885] Num frames 2300...
+[2024-07-24 19:42:07,240][02885] Avg episode rewards: #0: 9.285, true rewards: #0: 5.785
+[2024-07-24 19:42:07,242][02885] Avg episode reward: 9.285, avg true_objective: 5.785
+[2024-07-24 19:42:07,353][02885] Num frames 2400...
+[2024-07-24 19:42:07,483][02885] Num frames 2500...
+[2024-07-24 19:42:07,606][02885] Num frames 2600...
+[2024-07-24 19:42:07,736][02885] Num frames 2700...
+[2024-07-24 19:42:07,863][02885] Num frames 2800...
+[2024-07-24 19:42:08,001][02885] Num frames 2900...
+[2024-07-24 19:42:08,140][02885] Num frames 3000...
+[2024-07-24 19:42:08,261][02885] Avg episode rewards: #0: 9.900, true rewards: #0: 6.100
+[2024-07-24 19:42:08,264][02885] Avg episode reward: 9.900, avg true_objective: 6.100
+[2024-07-24 19:42:08,331][02885] Num frames 3100...
+[2024-07-24 19:42:08,460][02885] Num frames 3200...
+[2024-07-24 19:42:08,585][02885] Num frames 3300...
+[2024-07-24 19:42:08,716][02885] Num frames 3400...
+[2024-07-24 19:42:08,844][02885] Num frames 3500...
+[2024-07-24 19:42:09,015][02885] Avg episode rewards: #0: 9.805, true rewards: #0: 5.972
+[2024-07-24 19:42:09,017][02885] Avg episode reward: 9.805, avg true_objective: 5.972
+[2024-07-24 19:42:09,042][02885] Num frames 3600...
+[2024-07-24 19:42:09,178][02885] Num frames 3700...
+[2024-07-24 19:42:09,304][02885] Num frames 3800...
+[2024-07-24 19:42:09,429][02885] Num frames 3900...
+[2024-07-24 19:42:09,557][02885] Num frames 4000...
+[2024-07-24 19:42:09,683][02885] Num frames 4100...
+[2024-07-24 19:42:09,808][02885] Num frames 4200...
+[2024-07-24 19:42:09,892][02885] Avg episode rewards: #0: 9.889, true rewards: #0: 6.031
+[2024-07-24 19:42:09,898][02885] Avg episode reward: 9.889, avg true_objective: 6.031
+[2024-07-24 19:42:10,010][02885] Num frames 4300...
+[2024-07-24 19:42:10,151][02885] Num frames 4400...
+[2024-07-24 19:42:10,281][02885] Num frames 4500...
+[2024-07-24 19:42:10,407][02885] Num frames 4600...
+[2024-07-24 19:42:10,532][02885] Num frames 4700...
+[2024-07-24 19:42:10,664][02885] Num frames 4800...
+[2024-07-24 19:42:10,796][02885] Avg episode rewards: #0: 9.828, true rewards: #0: 6.077
+[2024-07-24 19:42:10,798][02885] Avg episode reward: 9.828, avg true_objective: 6.077
+[2024-07-24 19:42:10,849][02885] Num frames 4900...
+[2024-07-24 19:42:10,982][02885] Num frames 5000...
+[2024-07-24 19:42:11,111][02885] Num frames 5100...
+[2024-07-24 19:42:11,246][02885] Num frames 5200...
+[2024-07-24 19:42:11,371][02885] Num frames 5300...
+[2024-07-24 19:42:11,500][02885] Num frames 5400...
+[2024-07-24 19:42:11,626][02885] Num frames 5500...
+[2024-07-24 19:42:11,754][02885] Num frames 5600...
+[2024-07-24 19:42:11,883][02885] Num frames 5700...
+[2024-07-24 19:42:12,023][02885] Avg episode rewards: #0: 10.953, true rewards: #0: 6.398
+[2024-07-24 19:42:12,025][02885] Avg episode reward: 10.953, avg true_objective: 6.398
+[2024-07-24 19:42:12,082][02885] Num frames 5800...
+[2024-07-24 19:42:12,220][02885] Num frames 5900...
+[2024-07-24 19:42:12,345][02885] Num frames 6000...
+[2024-07-24 19:42:12,471][02885] Num frames 6100...
+[2024-07-24 19:42:12,601][02885] Num frames 6200...
+[2024-07-24 19:42:12,729][02885] Num frames 6300...
+[2024-07-24 19:42:12,868][02885] Num frames 6400...
+[2024-07-24 19:42:12,973][02885] Avg episode rewards: #0: 10.930, true rewards: #0: 6.430
+[2024-07-24 19:42:12,976][02885] Avg episode reward: 10.930, avg true_objective: 6.430
+[2024-07-24 19:42:51,453][02885] Replay video saved to /content/train_dir/default_experiment/replay.mp4!