o ci@s4dZddlmZddlmZmZGdddeZdS)a [1] Mastering Diverse Domains through World Models - 2023 D. Hafner, J. Pasukonis, J. Ba, T. Lillicrap https://arxiv.org/pdf/2301.04104v1.pdf [2] Mastering Atari with Discrete World Models - 2021 D. Hafner, T. Lillicrap, M. Norouzi, J. Ba https://arxiv.org/pdf/2010.02193.pdf )Learner)override5OverrideToImplementCustomLogic_CallToSuperRecommendedcs,eZdZdZeeefddZZS)DreamerV3LearnerzDreamerV3 specific Learner class. Only implements the `after_gradient_based_update()` method to define the logic for updating the critic EMA-copy after each training step. cs2tj|d|jjD] \}}|jq dS)N) timesteps)superafter_gradient_based_updatemodule _rl_modulesitemscritic update_ema)selfr module_idr  __class__d/home/ubuntu/.local/lib/python3.10/site-packages/ray/rllib/algorithms/dreamerv3/dreamerv3_learner.pyrs z,DreamerV3Learner.after_gradient_based_update) __name__ __module__ __qualname____doc__rrrr __classcell__rrrrrs rN)rray.rllib.core.learner.learnerrray.rllib.utils.annotationsrrrrrrrs