Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.91 +/- 95.24
+      value: -198.06 +/- 109.63
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 3e-05
 'num_envs': 16
-'num_steps': 128
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/LunarLander-v2PPO'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1685093857.2850cb3f29b2.19070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d03f88414144878e52f4838ec51f170964503733828d7541a9b20d912b80668
+size 62776

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f238183bd530af18095b9495069bd045a28eeebb48d75b7192596caedfa36c
+oid sha256:3d1691b0ac62d4f07f397614fceabacb0b78db867359737b6ade507380bfecab
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.9130156882699, "std_reward": 95.2404801664572, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:36:29.725655"}
+{"env_id": "LunarLander-v2", "mean_reward": -198.06125024553063, "std_reward": 109.62839906232786, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:37:56.419974"}