Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -227.63 +/- 138.42
+      value: 8.75 +/- 126.45
       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.1696537274.15a39c3109bd.11526.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c542e6bca99c69e7c8f0bdd818908ec753af2c1db6cce167fc362a6ee55edfaf
+size 1290992

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:2d7ca9d094a695f309c8f59fe5c7ada825cb4baebdecf651ad75721ad0e1b6e8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -227.6327465948569, "std_reward": 138.4161090267263, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-05T20:18:45.509850"}
+{"env_id": "LunarLander-v2", "mean_reward": 8.74733682404722, "std_reward": 126.44620353087562, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-05T20:51:18.719646"}