Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.90 +/- 52.05
+      value: -43.60 +/- 88.79
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1676891390.f42358022a8e.7353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86ef28b261015dcab16ecb30dbdcdcdbce8355df55dd85c23696aa378ba567c
+size 758809

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc6776ffcf3d1d3ad93b909bbbdffb4a97b058a84b907a6e688373311247d9e
+oid sha256:c249ec1640abbc7f1b60582d196b2666e6211fa59330b5401b5a0e0b8dc10acf
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.89720644727691, "std_reward": 52.04984104391134, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-20T11:00:28.059755"}
+{"env_id": "LunarLander-v2", "mean_reward": -43.59839234946049, "std_reward": 88.79243732371442, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-20T11:42:44.100874"}