Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -209.58 +/- 125.36
+      value: -218.70 +/- 92.08
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 5e-05
+'learning_rate': 7e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714947968.71d3fa3d3a00.13872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b8b6d40ff162ac8100055257c6555267a391482f0d94cb1d3dd88bc0d98bc4
+size 114166

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0792a2b515886e3c981b32975c6cd623782aaf2e473ea4c69586eefe0ff8736b
+oid sha256:8bb910849e57096a8ff50cb41728e1dd055fc2dec961eacf8724b1216e2d4b36
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -209.58183354426455, "std_reward": 125.36152561690162, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:24:27.788001"}
+{"env_id": "LunarLander-v2", "mean_reward": -218.70326690099583, "std_reward": 92.08052157290372, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:26:51.013601"}