Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -183.15 +/- 66.83
+      value: -157.91 +/- 95.24
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 3e-05
-'num_envs': 4
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/LunarLander-v2PPO'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1685093768.2850cb3f29b2.18642.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed4bb4a373a4ede0ec2fd4deeec14c8804ec5425b0961b4649372dc22ed5482
+size 71377

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a108327552bb500e57e82eaae0ae7ab5cad2dd9c012a2b4c88e642d5febe045c
+oid sha256:83f238183bd530af18095b9495069bd045a28eeebb48d75b7192596caedfa36c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -183.15377998821666, "std_reward": 66.83021323082126, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:34:42.709385"}
+{"env_id": "LunarLander-v2", "mean_reward": -157.9130156882699, "std_reward": 95.2404801664572, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:36:29.725655"}