Push agent to the Hub

README.md

@@ -1,12 +1,13 @@
 ---
 tags:
 - CartPole-v1
-- reinforce
+- ppo
+- deep-reinforcement-learning
 - reinforcement-learning
 - custom-implementation
-- deep-rl-class
+- deep-rl-course
 model-index:
-- name: cartpole-v1
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,12 +17,45 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 500.00 +/- 0.00
+      value: 203.30 +/- 123.31
       name: mean_reward
       verified: false
 ---
 
-  # **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
+  # 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
+'repo_id': 'kimnguyenwork/cartpole-v1'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
   

logs/events.out.tfevents.1694025227.535916435daa.5815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea9fa69c307feaaac6484ce7331b581cc5f027fd6f623b5292d222d7447f6cc
+size 109184

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34402f9e5e079c02306fe667e3d00144dbf4fd284c1b3abb804f9f384a775307
-size 2771
+oid sha256:5705843cd922e3a7e46bddd7ddcec1dba41eaa63d0fb0d22bc85ae5ff88e5df4
+size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-06T18:16:25.444884"}
+{"env_id": "CartPole-v1", "mean_reward": 203.3, "std_reward": 123.30616367400295, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-06T18:34:21.547215"}