!!python/object/apply:collections.OrderedDict - - - batch_size - 256 - - buffer_size - 1000000 - - gamma - 0.99 - - learning_rate - lin_7e-4 - - learning_starts - 10000 - - n_timesteps - 10000000.0 - - noise_std - 0.1 - - noise_type - normal - - policy - MlpPolicy - - policy_kwargs - dict(net_arch=[400, 300]) - - train_freq - 1