EfficientZero V2:在有限数据下掌握离散与连续控制
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
AI总结:
针对强化学习样本效率低、跨领域性能不稳定的问题,提出通用样本高效RL框架EfficientZero V2,拓展其适配多类动作与输入形式,在有限数据下多个基准的多数任务中优于现有SOTA及DreamerV3。
摘要:
样本效率仍是强化学习(RL)应用于现实任务时的核心挑战。尽管近期算法在提升样本效率方面取得了显著进展,但尚无算法能在不同领域中始终保持优异性能。本文提出了EfficientZero V2,这是一个为样本高效RL算法设计的通用框架。我们将EfficientZero的性能拓展至多个领域,涵盖连续与离散动作,以及视觉输入和低维输入。通过我们提出的一系列改进,在有限数据设置下,EfficientZero V2在各类任务中大幅优于当前的最优水平(SOTA)。EfficientZero V2相比主流通用算法DreamerV3取得了显著进步,在Atari 100k、本体控制(Proprio Control)、视觉控制(Vision Control)等不同基准的66项评估任务中,有50项取得了更优结果。
英文摘要:
Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior performance across diverse domains. In this paper, we introduce EfficientZero V2, a general framework designed for sample-efficient RL algorithms. We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs. With a series of improvements we propose, EfficientZero V2 outperforms the current state-of-the-art (SOTA) by a significant margin in diverse tasks under the limited data setting. EfficientZero V2 exhibits a notable advancement over the prevailing general algorithm, DreamerV3, achieving superior outcomes in 50 of 66 evaluated tasks across diverse benchmarks, such as Atari 100k, Proprio Control, and Vision Control.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。