Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -29.73 +/- 76.10
+      value: 82.25 +/- 103.65
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1686509752.b006ca1066e3.8599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6621d5e3c3cbc1333b3627311b574dfc8b65e6a0eebdd571676b040aed6b299e
+size 1296802

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f76c953c029480122c5a81a2516861b10770b48fee7ea05778eccfe553c84d
+oid sha256:16c14154a3239d4afb840cfc54bd5b1191d7ba55775f805d70c2dc0318a3d85c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -29.726122873786274, "std_reward": 76.0993557769261, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-11T18:54:29.858734"}
+{"env_id": "LunarLander-v2", "mean_reward": 82.25396135847986, "std_reward": 103.64935360610703, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-11T19:23:32.373961"}