Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.45 +/- 56.59
+      value: 13.23 +/- 112.33
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1684575787.Omen-117.1956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99371e4a68c28876ddc5baf510a562066392504a3959017f8db6aa12bfccf4d
+size 1291365

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3f19bede23eea4a4b1abcc462a8f3873451c661b9909cc76867f6685dca14c
+oid sha256:98d349153c1f22458064fa9acb6b638c1d658a8dd526509b0586ddf800f1f9d3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.45309953403967, "std_reward": 56.5946041412372, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-20T15:05:46.236099"}
+{"env_id": "LunarLander-v2", "mean_reward": 13.23292897186345, "std_reward": 112.32836675196481, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-20T15:43:30.139319"}