Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -214.15 +/- 79.68
+      value: 47.83 +/- 43.84
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1707919477.HARRY-MECHREV.20148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e405ba1c36a27065078786019ddf1cff8ac2233ec46c8508034c823f532d1af8
+size 664471

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c173727d7f2ce9c6b21abab5ec8d9055b8f2f751be4c4bb60354d5032d28c77
+oid sha256:e0868778f8cacaaae7a330f73e34e0bb6939783477682b8045dacc981b22c22c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -214.14575903369058, "std_reward": 79.67719012214913, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T21:03:14.745966"}
+{"env_id": "LunarLander-v2", "mean_reward": 47.82822964182912, "std_reward": 43.84395796563957, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T22:14:24.419330"}