Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -170.02 +/- 76.39
+      value: -198.16 +/- 80.99
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 25000
+'total_timesteps': 5000
 'learning_rate': 2e-05
 'num_envs': 3
 'num_steps': 64

logs/events.out.tfevents.1690591535.089e90cf7af3.2269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041118c345a7fe8ac22f2672211fdf625b01f5de1d110c7262e267bf3d7b2a99
+size 20233

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3750449b5f66a973f1bb9eb95e8a7a44a230184fe66d75d4d99fee5dee7916f3
+oid sha256:336b77695ecfadc07f5cca079d088660db4be9f8b511cb038295d183d41904a8
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -170.02054304900693, "std_reward": 76.39435714913401, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-28T22:09:48.932088"}
+{"env_id": "LunarLander-v2", "mean_reward": -198.15892075565608, "std_reward": 80.98747190780819, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-29T00:45:43.276908"}