Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 255.89 +/- 13.95
+      value: 115.55 +/- 70.33
       name: mean_reward
       verified: false
 ---
@@ -41,7 +41,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'num_envs': 4
-'num_steps': 512
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'FredericProtat/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1694872644.293f1447d12d.1806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab692b493d2f550f8169229e2f6672c73db0364adf7f0a9207e81b3841c92034
+size 1793599

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08adc4f22dd9c65dcdff08333571dd223fac3cee8e713dffe3705e7da86607b8
+oid sha256:96ac1d0154c6eb0418e39862f8b25495c8955c7f54317d5d9d7fd7f996f6fc33
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 255.89097883627375, "std_reward": 13.94997954387589, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-14T12:05:30.621901"}
+{"env_id": "LunarLander-v2", "mean_reward": 115.55130962292871, "std_reward": 70.33022400607449, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-16T15:55:59.428243"}