Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -111.96 +/- 88.86
+      value: -202.59 +/- 106.73
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.003
+'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1718027809.887b5cfc0142.22682.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36351a07dbfecd626ced86ffa357cef88d0c9af10a39f2d077abb1fc9a61140b
+size 71376

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49eb8f2da74322a0bbd6e7f6d60747ac0c75a7aa5aa690d355caf86caf7a9358
+oid sha256:34f58675720bf4efed99dae4cec87c6d904cf61335dde601479d9c4c93afd553
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -111.96160298495883, "std_reward": 88.85799312742037, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:54:26.604742"}
+{"env_id": "LunarLander-v2", "mean_reward": -202.58596074419802, "std_reward": 106.72833378979264, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:57:09.797548"}