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 2012.01100cs.LG
收藏

自校正Q学习

Self-correcting Q-Learning

Columbia University(哥伦比亚大学)

Rong Zhu, Mattia Rigotti

摘要:

已知Q-学习算法受到最大化偏差的影响,即动作值的系统性高估,这是最近重新受到关注的重要问题。双Q学习已经被提出作为一种有效的算法,以减轻这种偏见。然而,这是以低估动作值为代价的,除了增加的内存需求和较慢的收敛。在本文中,我们介绍了一种新的方法来解决的最大化偏差的形式“自我校正算法”近似的最大值的期望值。我们的方法平衡了传统Q学习中使用的单估计器的高估和双Q学习中使用的双估计器的低估。将该策略应用于Q学习,得到自校正Q学习。我们从理论上证明了这种新算法具有与Q学习相同的收敛保证,同时更准确。从经验上讲,它在高方差回报的域中表现得比双Q学习更好,甚至在零或低方差回报的域中比Q学习更快地收敛。这些优势转移到我们称之为自校正DQN的Deep Q Network实现中,并且在Atari 2600域中的几个任务上优于常规DQN和Double DQN。

英文摘要:

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence. In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.

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。

↑