Push agent to the Hub

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- LunarLander-v2
+- 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: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 230.81 +/- 20.92
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  ```python
+  {'path': '/content/drive/MyDrive/Colab Notebooks/HuggingFace/RL/Unit08'
+'name': 'ppo-LunaLander_1.pt'
+'env-id': 'LunarLander-v2'
+'agent_properties': {'num_layers': 2
+'hidden': 128
+'activation': 'Tanh'}
+'seed': ''
+'device': 'cuda'
+'total_timesteps': 100000
+'num_steps': 32768
+'batch_size': 64
+'update_epochs': 2
+'learning_rate': 1e-05
+'lr_schedule': 'Exp'
+'lr_final': 1e-06
+'gamma': 0.995
+'gae_lambda': 0.99
+'norm_adv': 'True'
+'clip_coef': 0.2
+'clip_vloss': 'False'
+'entropy_loss_coef': 0.01
+'value_loss_coef': 0.5
+'max_grad_norm': 0.5
+'n_eval_episodes': 10}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ec96972ddd578bac5547cc0dc02dcb63cbaf8437af45a0e9c18eb8054ae1a8
+size 8744

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 230.81007816168602, "std_reward": 20.91964137538508, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-30T10:57:57.096023"}