Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: HealthGatheringSupreme-v1
     metrics:
     - type: mean_reward
-      value: 5.00 +/- 2.80
+      value: 1.91 +/- 2.14
       name: mean_reward
       verified: false
 ---
@@ -34,13 +34,14 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'clip_coef': 0.2
-'total_timesteps': 1000000
-'recurrence': 32
-'ent_coef': 0.02
+'total_timesteps': 2000000
+'recurrence': 16
+'ent_coef': 0.001
 'vf_coef': 0.5
-'max_grad_norm': 40000.0
+'max_grad_norm': 4.0
 'epsilon': 0
 'num_minibatches': 1
-'update_epochs': 1}
+'update_epochs': 1
+'frame_skip': 4}
   ```
   

logs/events.out.tfevents.1721952272.tf-notebook-0.66053.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91354bf6bdcbe76c96d406a8cd573c8403b9d0ec2a3679ecc78f18c6c59e16cb
+size 1202971

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633e8213458e1f1d5c6db09e9538180bfaffba0855590984245640750d64272d
-size 14005790
+oid sha256:0698f2ed3063458f65aea6800a418ae30193982a7fde05dc01aa2e83caca2f0f
+size 16108110

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95972272778cb6cd36f064c7cc278f1b28818510f96fa04d91de05189dea
-size 227539
+oid sha256:ddfe49bd892471ed94b401c882ad8004541024a3917a4882960ba4b5b395392b
+size 23674

results.json

@@ -1 +1 @@
-{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 4.997199535369873, "std_reward": 2.8015787601470947, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-25T22:48:37.432289"}
+{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 1.9075994491577148, "std_reward": 2.1360208988189697, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T00:25:09.853065"}