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 2209.09185cs.ROcs.LG
收藏

基于上下文多臂老虎机的自主决策主动推理

Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits

University of Colorado Boulder(科罗拉多大学博尔德分校)

Shohei Wakayama, Nisar Ahmed

AI总结:

本文将主动推理引入上下文多臂老虎机决策,提出基于变分和拉普拉斯近似的期望自由能计算方法,以较低计算成本实现更少迭代和更优累积遗憾。

摘要:

在不确定性下的自主机器人决策中,必须考虑对可用选项的利用与探索之间的权衡。如果可以利用与选项相关的辅助信息,此类决策问题通常可以被表述为上下文多臂老虎机(CMABs)。在本研究中,我们将近年来在神经科学领域得到积极研究的主动推理应用于CMABs,作为一种替代的动作选择策略。与传统的动作选择策略不同,当计算与决策智能体概率模型相关的期望自由能(EFE)时,可以严格评估每个选项的不确定性,该期望自由能源自自由能原理。我们特别处理使用分类观测似然函数的情况,此时EFE值在解析上不可处理。我们引入了基于变分近似和拉普拉斯近似的计算EFE的新近似方法。大量仿真研究结果表明,与其他策略相比,主动推理通常需要少得多的迭代次数来识别最优选项,并且通常以相对较低的额外计算成本获得更优的累积遗憾。

英文摘要:

In autonomous robotic decision-making under uncertainty, the tradeoff between exploitation and exploration of available options must be considered. If secondary information associated with options can be utilized, such decision-making problems can often be formulated as contextual multi-armed bandits (CMABs). In this study, we apply active inference, which has been actively studied in the field of neuroscience in recent years, as an alternative action selection strategy for CMABs. Unlike conventional action selection strategies, it is possible to rigorously evaluate the uncertainty of each option when calculating the expected free energy (EFE) associated with the decision agent's probabilistic model, as derived from the free-energy principle. We specifically address the case where a categorical observation likelihood function is used, such that EFE values are analytically intractable. We introduce new approximation methods for computing the EFE based on variational and Laplace approximations. Extensive simulation study results demonstrate that, compared to other strategies, active inference generally requires far fewer iterations to identify optimal options and generally achieves superior cumulative regret, for relatively low extra computational cost.

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。

↑