!!python/object/apply:collections.OrderedDict - - - delta_std - 0.1 - - learning_rate - 0.018 - - n_delta - 4 - - n_envs - 1 - - n_timesteps - 2000000.0 - - n_top - 1 - - normalize - dict(norm_obs=True, norm_reward=False) - - policy - MlpPolicy - - policy_kwargs - dict(net_arch=[16]) - - zero_policy - false