Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 216.00 +/- 104.80
+      value: 226.40 +/- 70.72
       name: mean_reward
       verified: false
 ---
@@ -25,37 +25,6 @@ model-index:
   # PPO Agent Playing CartPole-v1
 
   This is a trained model of a PPO agent playing CartPole-v1.
-    
+
   # Hyperparameters
-  ```python
-  {'exp_name': 'ppo'
-'seed': 1
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'CartPole-v1'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'batch_size': 512
-'minibatch_size': 128
-'repo_id': 'dgenes/ppo-CartPole-v1'}
-  ```
   

logs/events.out.tfevents.1771948255.30feefec134f.2975.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cebc306be07239873a9da6620fca988d6ce91c22f01797eff95ab710c7044c6
+size 50365

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8865abc247bff256128181f16fb7ad9798aea79e02fa427e38546352a52a5c85
+oid sha256:254c93ec02a378dc348204e61579272db90c3aadd50f83fdb92e38b4e11261c9
 size 40859

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 216.0, "std_reward": 104.79790074233358, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-24T13:59:53.012947"}
+{"env_id": "CartPole-v1", "mean_reward": 226.4, "std_reward": 70.71944569918517, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-24T16:15:57.215960"}