Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -105.43 +/- 14.69
+      value: -109.57 +/- 45.70
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00102
+'learning_rate': 0.01
 'num_envs': 5
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1701202331.e705ad2e6486.23268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afe8f0ea1958caf453c12604a7e166d96d490c68d9de43b023286f07f8b8fee
+size 112254

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9eb81c53cff29c5617b9c7c4505da1f6ed4c6ad41fb1151112e75d82d8fd3c
+oid sha256:b3312936c37ffcf1209830036f23598060c70388e050a83807984ba8b9e5b04b
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -105.42594018437653, "std_reward": 14.68530217238398, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:11:19.705927"}
+{"env_id": "LunarLander-v2", "mean_reward": -109.57283445744834, "std_reward": 45.69967290235556, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:15:27.667271"}