Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -144.96 +/- 99.25
+      value: -150.17 +/- 94.68
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 1024
+'num_envs': 16
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.1
 'target_kl': None
 'repo_id': 'DavidCollier/ppo-LunarLander-v2-unit8'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1704519127.cef9efba8278.5547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a8aefe443cc1881e3fc8db2ba0e2e7307fcf67a5b1b5a14524e0faa906ed27
+size 70268

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163a97067fb60a373d8a803c091b7bba3b59c72af1c6a9105ac38c15e9fcb907
+oid sha256:1d5fbedffc8c79dd506431905593d9700a103dc205b1bc21eefe337f19af07e8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -144.95974399713947, "std_reward": 99.25028426589334, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:31:03.786220"}
+{"env_id": "LunarLander-v2", "mean_reward": -150.16645272715908, "std_reward": 94.67704618396218, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:32:28.291765"}