Initial commit

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -154.53 +/- 95.61
+      value: -64.00 +/- 19.54
       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

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c7fdb910e2a91cdcfe0138117e5cd13f70747a6bf07102247945e267ac3c57
+oid sha256:3a495681ed0715e3e84e02ed2970c8ac4c7eba5781e4319e364a1f58d8afd5a5
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -154.53317358910698, "std_reward": 95.61409765778531, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-03T19:42:32.695460"}
+{"env_id": "LunarLander-v2", "mean_reward": -64.00075579713192, "std_reward": 19.541288934197084, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-03T19:59:15.945122"}