Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -7.88 +/- 55.09
+      value: -179.78 +/- 154.45
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
-'learning_rate': 0.00025
+'total_timesteps': 45000
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1676758447.5f9cb58b9b05.8433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de11a00c256eccf5433461f4b624b2761ef4b73f6d1f481aab6932e6f1a659a
+size 89922

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b34ece5b9b73c63f2fe5f8d3054cf55b7de578990279f4caafb1bc9dbc27a5
-size 42597
+oid sha256:b57842bb6212b6cc2f58a07696226ff7ee66650cbc3119e3ca05853b714d8bb0
+size 142801

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -7.882044834539921, "std_reward": 55.08888047410135, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T21:57:40.240758"}
+{"env_id": "LunarLander-v2", "mean_reward": -179.77814168237052, "std_reward": 154.4457817373032, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T22:14:54.498923"}