SpaceInvadersNoFrameskip-v4: env_wrapper: - stable_baselines3.common.atari_wrappers.AtariWrapper frame_stack: 4 policy: 'CnnPolicy' n_timesteps: !!float 1e4 buffer_size: 100000 learning_rate: !!float 1e-4 batch_size: 32 learning_starts: 100000 target_update_interval: 1000 train_freq: 4 gradient_steps: 1 exploration_fraction: 0.1 exploration_final_eps: 0.01 # If True, you need to deactivate handle_timeout_termination # in the replay_buffer_kwargs optimize_memory_usage: False