Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -185.77 +/- 126.52
+      value: -12.59 +/- 46.45
       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': 0.0001
 'num_envs': 4
 'num_steps': 1024

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89530fdeee59b7cf0a358e0096a8df0c72de422f8661c4f48bf4b338f5fe59a
+oid sha256:58ed15663e5229a47f68c44ac53604c002eb8ac4ab894d2b8905f6677e352af8
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -185.7701144021438, "std_reward": 126.51731995346864, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:09:07.272181"}
+{"env_id": "LunarLander-v2", "mean_reward": -12.586352569917254, "std_reward": 46.44567552178459, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:17:48.899658"}