Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.55 +/- 65.69
+      value: -203.59 +/- 124.98
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 40000
+'total_timesteps': 60000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1740282764.c4d29affe86f.27404.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2f5c43bab3ec31a5106dd27339ecf1a2b594767c43419ad449fbe2e0b9930e
+size 134017

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737b05901f8f46a2e5b029df1facd2c5f91bf2654b0e2e116d2f40344a2f8388
+oid sha256:6cccb1dab1115d85ad2bee123f50d7c5f549dda0a778a5fa6ef1bfdc8cc0f9a8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.54807756325675, "std_reward": 65.68773392197824, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T03:36:28.122069"}
+{"env_id": "LunarLander-v2", "mean_reward": -203.5899025683648, "std_reward": 124.9758524703905, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T03:53:31.610652"}