Push agent to the Hub

README.md

@@ -0,0 +1,62 @@
+---
+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: 125.70 +/- 62.02
+      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.py'
+'gym_id': 'LunarLander-v2'
+'seed': 1
+'learning_rate': 0.00025
+'total_timesteps': 25000
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'CartPole-v1'
+'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': 'lsaulier/ppo-CartPole-v1'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1677679667.d5a9a758cc58.183.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71ec3f4b0e0ec0f5633e0ae3aca05b32d41e06d559e8cc5dbdbcb1dd72d040e
+size 76911

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd036f33f736d6e258767cd77a7b59fcf9b4b2a345739a14299a37f0526aa27
+size 40037

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 125.7, "std_reward": 62.02104481544954, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T14:08:04.998824"}