Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 422.20 +/- 113.27
+      value: 500.00 +/- 0.00
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 300000
+'total_timesteps': 400000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1678051201.7d483674e272.14166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e00ced716f2b8805ea5d57b0ac6ce0657143b0bb3a6b0616a3a70470fa4eed
+size 562251

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4557a3416baf75352fdc1e83a02def4792705158c7afae6581357602db0356dc
+oid sha256:c75f10ebc8506c703d03f0e29d6c168f78fb2bc36a967fb2125bbfb7fc4ee051
 size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 422.2, "std_reward": 113.27471032847535, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-05T21:19:06.536457"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-05T21:23:59.094639"}