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: 96.70 +/- 99.97
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'experiment_name': 'final3'
+'env_name': 'LunarLander-v2'
+'learning_rate': 0.0003
+'seed': 1
+'total_timesteps': 125000
+'num_envs': 4
+'num_steps': 128
+'torch_deterministic': True
+'cuda': True
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 4
+'update_epochs': 10
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'save_video': True
+'batch_size': 512
+'mini_batch_size': 128}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ad939122665ffc91aa3a86db8445420ba13f4977443f2bad15f9c430ab647c
+size 147521

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 96.70262636667965, "std_reward": 99.97299481482274, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-11T23:54:56.018749"}