Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 498.50 +/- 4.50
+      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': 200000
+'total_timesteps': 400000
 'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1684220746.78ed759377b8.3357.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97542ec499bf48a2aa19c161793ff255c44b5dc0e4a4be800ca17d99155779a
+size 402662

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967b12033ec6da76c10c55c24f5f135d5f63c023361b83f4e15e490e70e3048f
+oid sha256:97e04c6cee6cb3fb21b46f27b34a0ee232836f6acfd48008ccdc11f4df465ccf
 size 39909

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 498.5, "std_reward": 4.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T07:05:04.537188"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T07:08:19.480120"}