Initial commit

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.93 +/- 111.55
+      value: -43.70 +/- 16.05
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a69b7bcd30a64cd0e3f59fb043b7222208fabadead1211be73df47a6003ac3e
+oid sha256:3a495681ed0715e3e84e02ed2970c8ac4c7eba5781e4319e364a1f58d8afd5a5
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.93470284522232, "std_reward": 111.5488000959182, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-06T20:12:44.691942"}
+{"env_id": "LunarLander-v2", "mean_reward": -43.69973330414964, "std_reward": 16.04576723751674, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-06T20:39:05.894522"}