Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -19.27 +/- 104.85
+      value: -55.80 +/- 93.24
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 550000
-'learning_rate': 0.0003
+'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 64
+'num_steps': 32
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'kinkpunk/PPO-LunarLander'
-'batch_size': 256
-'minibatch_size': 64}
+'batch_size': 128
+'minibatch_size': 32}
   ```
   

logs/events.out.tfevents.1676836424.e00ba7557307.26209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e7b6beb8e04256788a1ad7b85e882ce2107c1a9fa469a543fcb48c729e3116
+size 2386809

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb075921cc57032de8d2c54a3d8020228c3c36a9b81a8373e546459766dc6b44
+oid sha256:7af0214800ada59a1a4fc3d93cb2c137eab1631b43e8dd909dcf0c46bb5ca13b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -19.26867141198583, "std_reward": 104.8509735668682, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T19:52:14.632448"}
+{"env_id": "LunarLander-v2", "mean_reward": -55.79561226201317, "std_reward": 93.24380743018068, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T20:12:03.021254"}