Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -204.31 +/- 150.48
+      value: 31.22 +/- 119.76
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1690784045.980c38cbb143.8632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15633dd4496cf7fcb2a0749de55264aa0ce02338ff8655bc1dc1a7d37d3f426
+size 1296803

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:16c14154a3239d4afb840cfc54bd5b1191d7ba55775f805d70c2dc0318a3d85c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -204.31351241972214, "std_reward": 150.47678596540254, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-31T06:10:57.425635"}
+{"env_id": "LunarLander-v2", "mean_reward": 31.224885080469402, "std_reward": 119.7587261863333, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-31T06:40:10.973761"}