!!python/object/apply:collections.OrderedDict - - - env_wrapper - - stable_baselines3.common.atari_wrappers.AtariWrapper - - frame_stack - 4 - - n_envs - 16 - - n_timesteps - 500000.0 - - policy - CnnPolicy - - policy_kwargs - dict(optimizer_class=RMSpropTFLike, optimizer_kwargs=dict(eps=1e-5)) - - vf_coef - 0.25