{
    "total_timesteps": 40000000,
    "policy": "MlpPolicy",
    "policy_kwargs" : {
        "features_extractor_class" : "NatureCNN",
    "activation_fn" : "nn.ReLU",
    "net_arch" : "dict(vf=[512, 256], pi=[256, 128])"
    },
    "learning_rate" : "linear_schedule(3e-4,1e-6)",
    "n_steps" : 256,
    "batch_size" : 1024,
    "n_epochs" : 4,
    "gamma" : 0.99,
    "gae_lambda" : 0.95,
    "clip_range" : 0.1,
    "vf_coef" : 0.5,
    "ent_coef" : 0.01
}