Push agent to the Hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- CartPole-v1
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 29.30 +/- 14.59
+      name: mean_reward
+      verified: false
+---
+
+    # PPO Agent Playing CartPole-v1
+
+    This is a trained model of a PPO agent playing CartPole-v1.
+      
+    # Hyperparameters
+    ```python
+    {'exp_name': 'ppo-experiment'
+'repo_id': 'Priyam05/ppo-CartPole-v1'
+'gym_id': 'CartPole-v1'
+'learning_rate': 0.00025
+'min_learning_rate_ratio': 0.1
+'seed': 1
+'total_timesteps': 25000
+'torch_not_deterministic': False
+'no_cuda': False
+'capture_video': False
+'hidden_size': 64
+'num_hidden_layers': 1
+'activation': 'tanh'
+'num_checkpoints': 4
+'num_envs': 4
+'num_steps': 128
+'no_lr_annealing': False
+'no_gae': False
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 4
+'num_update_epochs': 4
+'no_advantage_normalization': False
+'clip_coef': 0.2
+'no_value_loss_clip': False
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'batch_size': 512
+'minibatch_size': 128}
+    ```
+    

results.json

@@ -0,0 +1 @@
+{"env_id": null, "mean_reward": 29.3, "std_reward": 14.588008774332431, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-29T23:30:00.446563"}