{ "batch_size": 512, "clip_coef": 0.2, "cuda": true, "ent_coef": 0.01, "env_id": "LunarLander-v2", "exp_name": "ppo", "gae_lambda": 0.95, "gamma": 0.99, "learning_rate": 0.00025, "max_grad_norm": 0.5, "num_envs": 4, "num_minibatches": 4, "num_steps": 128, "total_timesteps": 50000, "update_epochs": 4, "vf_coef": 0.5 }