arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.04104cs.AIcs.LGstat.ML
收藏

通过世界模型掌握多样化领域

Mastering Diverse Domains through World Models

Google DeepMind(谷歌DeepMind);University of Toronto(多伦多大学)

Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap

AI总结:

针对强化学习算法跨领域需大量调参的难题,提出通用算法DreamerV3,靠世界模型与鲁棒技术以单一配置在超150项任务中胜出,还首次无人工干预在Minecraft中从零收集钻石,拓宽强化学习适用范围。

摘要:

开发一种能学习解决广泛应用中各类任务的通用算法,一直是人工智能领域的一项核心挑战。尽管当前的强化学习算法可轻松应用于与其开发目标相似的任务,但要将它们配置到新的应用领域,仍需大量人类专业知识与实验。我们提出DreamerV3,这是一种通用算法,仅用单一配置,就能在超过150项多样化任务上超越专用方法。Dreamer会学习环境模型,并通过想象未来场景优化自身行为。基于归一化、平衡化和变换的鲁棒性技术,可实现跨领域的稳定学习。Dreamer可直接开箱即用,是首个在无需人类数据或课程的情况下,从零开始在Minecraft中收集到钻石的算法。这一成果被视为人工智能领域的一项重大挑战,要求在开放世界中从像素输入和稀疏奖励里探索具有长远眼光的策略。我们的工作无需大量实验就能解决具有挑战性的控制问题,让强化学习具备更广泛的适用性。

英文摘要:

Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires significant human expertise and experimentation. We present DreamerV3, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behavior by imagining future scenarios. Robustness techniques based on normalization, balancing, and transformations enable stable learning across domains. Applied out of the box, Dreamer is the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula. This achievement has been posed as a significant challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.

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。

↑