Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -133.38 +/- 85.79
+      value: 25.48 +/- 76.06
       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.1680272425.7ed8a96f547c.3480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106012579cab2ab611eafdbb4aa6cea65c268b68b2e06fc4ef8e242416b60f8f
+size 658621

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
+oid sha256:600a312f67eb1d1b4f09a512dbdc63169bdfd520e9315f53e0039492a38fb5c4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -133.38202133469431, "std_reward": 85.7914573859978, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-31T14:19:03.277357"}
+{"env_id": "LunarLander-v2", "mean_reward": 25.481526612793143, "std_reward": 76.05691003618624, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-31T14:35:23.063727"}