Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -171.59 +/- 103.32
+      value: 1.08 +/- 59.41
       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

logs/events.out.tfevents.1691392280.801e54b32575.7787.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b920a1d575194e58b3824e68ac8c55d5a3dd4b76e0a157846ce5b7c1bfae4f4
+size 675228

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -171.58919669334938, "std_reward": 103.32163148764403, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-07T07:09:10.144995"}
+{"env_id": "LunarLander-v2", "mean_reward": 1.0832669532358807, "std_reward": 59.408924317500464, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-07T07:25:59.832631"}