arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04046cs.LGcs.AI
收藏

无学习率强化学习:面向非平稳目标模型选择的案例研究

Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives

Boston University(波士顿大学);Broad Institute of MIT and Harvard(麻省理工学院与哈佛学院博德研究所)

Aida Afshar, Aldo Pacchiano

AI总结:

本文提出一种仅依赖奖励反馈、与具体RL算法和优化器无关的无学习率模型选择框架,可动态选择最优学习率,并通过实验证明在非平稳目标下数据驱动模型选择优于标准老虎机算法。

摘要:

强化学习(RL)算法的性能对超参数的选择非常敏感,其中学习率的影响尤为显著。当学习率设置不当时,RL算法要么无法收敛,要么需要大量样本。在本工作中,我们证明了模型选择有助于改善因学习率次优选择而导致的RL失败模式。我们提出了一个面向无学习率强化学习(Learning Rate-Free Reinforcement Learning)的模型选择框架,该框架采用模型选择方法在运行过程中动态选择最优学习率。这种自适应学习率调节方法既不依赖于底层的RL算法,也不依赖于优化器,仅利用奖励反馈来选择学习率;因此,该框架可以接收任意RL算法并生成其无学习率版本。我们针对策略优化方法进行了实验,并在框架内评估了多种模型选择策略。实验结果表明,当超参数的最优选择具有时间依赖性且非平稳时,数据驱动的模型选择算法是标准老虎机(bandit)算法的更优替代方案。

英文摘要:

The performance of reinforcement learning (RL) algorithms is sensitive to the choice of hyperparameters, with the learning rate being particularly influential. RL algorithms fail to reach convergence or demand an extensive number of samples when the learning rate is not optimally set. In this work, we show that model selection can help to improve the failure modes of RL that are due to suboptimal choices of learning rate. We present a model selection framework for Learning Rate-Free Reinforcement Learning that employs model selection methods to select the optimal learning rate on the fly. This approach of adaptive learning rate tuning neither depends on the underlying RL algorithm nor the optimizer and solely uses the reward feedback to select the learning rate; hence, the framework can input any RL algorithm and produce a learning rate-free version of it. We conduct experiments for policy optimization methods and evaluate various model selection strategies within our framework. Our results indicate that data-driven model selection algorithms are better alternatives to standard bandit algorithms when the optimal choice of hyperparameter is time-dependent and non-stationary.

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。

↑