Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.66 +/- 49.19
+      value: 1.86 +/- 84.95
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1722089765.42f4e18a5747.27051.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231834255e98222b343b1b35f5adfd4f4fd080e9655225a6b742b9b8a8bf2da6
+size 1255273

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d6b7c9a208a495425f19f065fe3f8c9ec095ca9d74bc49cc055a0194538f2b
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.6557380513759, "std_reward": 49.18511069380058, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-27T14:14:21.041776"}
+{"env_id": "LunarLander-v2", "mean_reward": 1.8635967308207035, "std_reward": 84.94626467569097, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-27T14:43:53.163635"}