Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -143.03 +/- 116.55
+      value: -33.79 +/- 24.42
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1681659590.5752da4520f0.27935.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42bf9a9dca15ab6244a5844bc62040187b3386bb803c8f8f7e2ed8453a7b27a
+size 768646

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161887ec352c6f3c45cbef7b9d7ebf7970714fcb9a65d63de3f566488fb4dea5
+oid sha256:99098509a7e50fead4acee96cc8510a87e478819b50952e264d602d76b08e34f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.02516734536079, "std_reward": 116.54659322641987, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-16T15:38:35.847951"}
+{"env_id": "LunarLander-v2", "mean_reward": -33.792368740821146, "std_reward": 24.416156763025082, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-16T16:57:18.348757"}