Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -49.29 +/- 46.82
+      value: -66.61 +/- 24.07
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1707099092.0cebaf678b8a.6886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290b1afebdcd4aeb0d1687bc8029ab3ced1704c09c27a56ea131c5a13e2e6fa4
+size 1235323

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
+oid sha256:4bab62617dee61f1306b075d08c5031f47552a39ea30c380840904fab1b528b7
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -49.28843496780259, "std_reward": 46.816925541768995, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-05T02:10:24.495552"}
+{"env_id": "LunarLander-v2", "mean_reward": -66.6133058708748, "std_reward": 24.070994220237004, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-05T02:40:08.336720"}