PPO Agent — LunarLander-v3
Mean reward: 254.86 ± 69.90 (10 episodes)
Hyperparameters
{'env_id': 'LunarLander-v3', 'total_timesteps': 500000, 'learning_rate': 0.0003, 'num_envs': 4, 'num_steps': 512, 'num_minibatches': 32, 'update_epochs': 4, 'gamma': 0.99, 'gae_lambda': 0.95, 'clip_coef': 0.2, 'ent_coef': 0.01, 'vf_coef': 0.5, 'max_grad_norm': 0.5, 'repo_id': 'pangshengwei/ppo-lunar-lander', 'seed': 1, 'cuda': True, 'no_hub': False, 'capture_video': False, 'batch_size': 2048, 'minibatch_size': 64}