Push agent to the Hub

README.md

@@ -0,0 +1,54 @@
+---
+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: 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.
+    
+  # Hyperparameters
+  ```python
+  {'env_id': 'CartPole-v1'
+'seed': 1
+'num_envs': 8
+'pi_hidden_layers': (64
+64)
+'v_hidden_layers': (64
+64)
+'learning_rate': 0.001
+'anneal_lr': True
+'total_timesteps': 100000
+'num_steps': 32
+'gamma': 0.98
+'gae_lambda': 0.8
+'num_minibatches': 1
+'num_epochs': 20
+'norm_advantage': True
+'clip_coef': 0.2
+'clip_vloss': True
+'vf_coef': 0.5
+'ent_coef': 0.0
+'max_grad_norm': 0.5
+'target_kl': None}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d16194938666c58a0dd96cba1a3b19f3242156cbdd5e359ddc235f8607ff233
+size 40037

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:50:48.703033"}