Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -212.33 +/- 79.08
+      value: -166.91 +/- 118.98
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 8e-05
+'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714947441.71d3fa3d3a00.11514.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede7676e2706adcff1c1e21a3a04473b79dea0637d39d79cb5a1913046a4d44d
+size 115904

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf33b799dbb26da9c9ef850fc4b4b977abc79c9db1605c0f4535a92481708dcc
+oid sha256:e2ff7b2ba7d837e96eadf2863aa54376cd243801fbd38386ec551124dea5a123
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.3316276668226, "std_reward": 79.08048582279538, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:15:41.934296"}
+{"env_id": "LunarLander-v2", "mean_reward": -166.90886025471758, "std_reward": 118.97865529814494, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:18:04.102540"}