Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.17 +/- 94.68
+      value: -241.30 +/- 150.28
       name: mean_reward
       verified: false
 ---
@@ -38,8 +38,8 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 16
+'learning_rate': 2.5e-05
+'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.1
 'target_kl': None
 'repo_id': 'DavidCollier/ppo-LunarLander-v2-unit8'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1704519260.cef9efba8278.6151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff90b9163f248b3a66d0ff50c859f0b7b442f35add588b911ab3864b219c3a4
+size 114061

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5fbedffc8c79dd506431905593d9700a103dc205b1bc21eefe337f19af07e8
+oid sha256:69749449f7aeed668bfcf9e756c7caf34decbab0fef4b633fc5164d6ec210c51
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.16645272715908, "std_reward": 94.67704618396218, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:32:28.291765"}
+{"env_id": "LunarLander-v2", "mean_reward": -241.30284348122964, "std_reward": 150.27613006674466, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:35:02.424957"}