Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 234.50 +/- 101.95
+      value: 253.70 +/- 119.96
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1675384842.lokman-system76-pc.428546.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9ef326728e9ab18f5d7b884a6671cf22463a10fce3112c2d1a7273ae1fef7a
+size 179856

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec55ec71f5a3e0de628dd33c0d1e776f1e8f526b857dd4650ca7ad9cc4086a54
+oid sha256:9db0d5659bf71d533c90f4907eea39d550627a10c6f5d550809c6b98f6051787
 size 40257

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 234.5, "std_reward": 101.94925208161166, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-02T16:39:25.859827"}
+{"env_id": "CartPole-v1", "mean_reward": 253.7, "std_reward": 119.9633694091659, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-02T16:41:42.066063"}