MTahaB/ppo-LunarLander-v2

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2.

Hyperparameters

{'env_id': 'LunarLander-v2'
'total_timesteps': 500000
'num_envs': 4
'algorithm': 'PPO'
'gym_version': '0.22.0'}