Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 28.40 +/- 11.76
+      value: 288.30 +/- 129.29
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 50000
+'total_timesteps': 400000
 'learning_rate': 0.00025
 'num_envs': 32
 'num_steps': 128

logs/events.out.tfevents.1685095040.2850cb3f29b2.24905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc78a9541501101008547323e088e495d2d6f87d4b08d511ec64ae9cc1066891
+size 425518

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8cb3abc4f583430e596fe0257fd97f5a2f0d98759dba929ec22a10b2439d2d
+oid sha256:9c7b6f34de3c9e6170be10d3a57822f968b81963214a64b0bef5e0ebc72a9d62
 size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 28.4, "std_reward": 11.757550765359255, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:56:30.845670"}
+{"env_id": "CartPole-v1", "mean_reward": 288.3, "std_reward": 129.29272988068587, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:58:07.684595"}