Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -38.55 +/- 176.12
+      value: -22.49 +/- 173.08
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1717189309.55cb65d93e82.12968.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f9b55b9fae29187bab1b5efb1a609b5d94b4482c3835d678b181a220a39943
+size 1717195

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bbbbc9835a0dbf82ecf6e6597e20fb69be5893221de6190376a94b9f9e31338
+oid sha256:d8ac9be4b79ccb7b27d1c990f6a6eb37d833fb01d541872ecc26942fdb3681d7
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -38.54949345696917, "std_reward": 176.1194113935721, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-31T20:54:37.604891"}
+{"env_id": "LunarLander-v2", "mean_reward": -22.48916359627649, "std_reward": 173.08368149292778, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-31T21:54:55.540898"}