Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -207.37 +/- 111.25
+      value: -187.95 +/- 124.68
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'timjwhite/LunaLander-Unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1689397956.156f3702c70c.14019.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0106e638e3eca565614394ff77f0882d6b8eb230dbd8e388bc3d225ed0bf80e
+size 87729

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:fe528db225a277544416c5478a1460cf04a3469338e69e027c3736186fbb37d0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -207.3694871071379, "std_reward": 111.2479466716846, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T04:46:48.781545"}
+{"env_id": "LunarLander-v2", "mean_reward": -187.95270437415948, "std_reward": 124.67723567063389, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T05:13:19.188866"}