Upload . with huggingface_hub

README.md

@@ -1,13 +1,12 @@
 ---
 tags:
 - CartPole-v1
-- ppo
-- deep-reinforcement-learning
+- reinforce
 - reinforcement-learning
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: PPO
+- name: ppo-CartPole-v1
   results:
   - task:
       type: reinforcement-learning
@@ -17,47 +16,12 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 174.40 +/- 46.67
+      value: 500.00 +/- 0.00
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
-
-  This is a trained model of a PPO agent playing CartPole-v1.
-  To learn to code your own PPO agent and train it Unit 8 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit8
-  
-  # Hyperparameters
-  ```python
-  {'f': '/root/.local/share/jupyter/runtime/kernel-fbe28e80-06f3-4c7b-af34-ae8d70502964.json'
-'exp_name': 'PPO_experiment_001'
-'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
-'repo_id': 'ThomasSimonini/ppo-CartPole-v1'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
+  # **Reinforce** Agent playing **CartPole-v1**
+  This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
+  To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
   

hyperparameters.json

@@ -0,0 +1 @@
+{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b16889548cc2a734518cfe265955eb0751aa930ce9f194ee84d3947d2fb9715
-size 39909
+oid sha256:b39f8c382b211832240c0f32d696b2a8b376a08b608f057ab5833465a7393798
+size 2579

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 174.4, "std_reward": 46.673761365461, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T09:09:05.236698"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T07:00:37.624017"}