!!python/object/apply:collections.OrderedDict - - - alive_bonus_offset - -1 - - delta_std - 0.025 - - learning_rate - 0.015 - - n_delta - 60 - - n_envs - 1 - - n_timesteps - 75000000.0 - - n_top - 20 - - normalize - dict(norm_obs=True, norm_reward=False) - - policy - LinearPolicy