Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -123.01 +/- 56.35
+      value: 68.78 +/- 111.62
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677345908.d57c8ab0d1e2.17216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c1c9c1bc9cfecad15841a14817dfef1a3496c065d6765f2fd1b202d01edc40
+size 637526

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169acbbfab735236e727bdcd143764cecb2e4a8b3fc00c4664c7bb56fe7a8c8b
+oid sha256:a486ff2fefc525537c908541110ecb75387fd679ca987e397b5ef68cbea54b19
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -123.01457843526097, "std_reward": 56.35138651942254, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T17:24:26.221575"}
+{"env_id": "LunarLander-v2", "mean_reward": 68.77963847840893, "std_reward": 111.62394613648465, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T17:38:15.424023"}