Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 37.64 +/- 94.83
+      value: 57.04 +/- 104.43
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.0003
+'learning_rate': 0.0002
 'num_envs': 16
-'num_steps': 2048
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'dungtd2403/ppo-Lunarlander-v1-unit8'
-'batch_size': 32768
-'minibatch_size': 1024}
+'batch_size': 8192
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1683016555.katana.34148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43aafceb7a6354c9c3aa23d20888a49cefcb153793b8baa62d11aaf4c1d8b39f
+size 299559

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090d1fb92a2c7d388e82d0f37c5b6fb94a43aeef84c05e34445be0ce088f7995
+oid sha256:76f3dc2b845ab6fdd67310a81e62b1157b19a18eebbc838830ea09bbb8841b86
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 37.63773463388161, "std_reward": 94.83346111302924, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T15:33:44.823012"}
+{"env_id": "LunarLander-v2", "mean_reward": 57.04470934013932, "std_reward": 104.42640681212369, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T16:01:57.804586"}