Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 184.20 +/- 67.10
+      value: 218.80 +/- 68.25
       name: mean_reward
       verified: false
 ---
@@ -25,7 +25,7 @@ model-index:
     # PPO Agent Playing CartPole-v1
 
     This is a trained model of a PPO agent playing CartPole-v1.
-    
+
     # Hyperparameters
     ```python
     {'exp_name': 'experiment'
@@ -37,7 +37,7 @@ 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.1739701803.26e15e277ccc.750.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad8a1e921ba7b63d44cecfec8306c2797b2a189a4fa6e62a270688d20303f73
+size 174801

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd16babc963802f3a659e2dd9d811e8388faf60e12e9d17635e4589fb103e41
+oid sha256:be422b0fb81fef0e0a8a713f02892c3a4b1b02ee217985a4c9b3a229c47fc2df
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 184.2, "std_reward": 67.10111772541498, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T09:32:18.569952"}
+{"env_id": "CartPole-v1", "mean_reward": 218.8, "std_reward": 68.24631858203048, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T10:31:05.178861"}