arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.01495cs.LGstat.ML
收藏

有界风险敏感马尔可夫博弈:基于迭代推理和累积前景理论的前向策略设计和反向奖励学习

Bounded Risk-Sensitive Markov Games: Forward Policy Design and Inverse Reward Learning with Iterative Reasoning and Cumulative Prospect Theory

University of California, Berkeley(加州大学伯克利分校)

Ran Tian, Liting Sun, Masayoshi Tomizuka

摘要:

经典的博弈论方法在多智能体系统的正向策略设计问题和反向奖励学习问题中,通常会做出强合理性假设:智能体在不确定性下完美地最大化期望效用。然而,这些假设与观察到的人类行为(如满足次优、风险寻求和损失规避决策)基本不匹配。本文研究了有界风险敏感马尔可夫博弈(BRSMG)及其逆报酬学习问题,用于人类现实行为的建模和人类行为模型的学习。利用迭代推理模型和累积前景理论,我们认为人类具有有限的智力,并在BRSMG中最大化风险敏感的效用。在BRSMG框架下,建立了正向策略设计和反向奖励学习问题的收敛性分析。我们验证了所提出的前向策略设计和反向奖励学习算法在导航场景。结果表明,代理人的行为表现出风险规避和风险寻求的特点。此外,在反向奖励学习任务中,所提出的有界风险敏感的反向学习算法优于基线风险中性的反向学习算法,通过有效地恢复不仅更准确的奖励值,而且智能水平和风险度量参数给定的代理的交互行为的演示。

英文摘要:

Classical game-theoretic approaches for multi-agent systems in both the forward policy design problem and the inverse reward learning problem often make strong rationality assumptions: agents perfectly maximize expected utilities under uncertainties. Such assumptions, however, substantially mismatch with observed humans' behaviors such as satisficing with sub-optimal, risk-seeking, and loss-aversion decisions. In this paper, we investigate the problem of bounded risk-sensitive Markov Game (BRSMG) and its inverse reward learning problem for modeling human realistic behaviors and learning human behavioral models. Drawing on iterative reasoning models and cumulative prospect theory, we embrace that humans have bounded intelligence and maximize risk-sensitive utilities in BRSMGs. Convergence analysis for both the forward policy design and the inverse reward learning problems are established under the BRSMG framework. We validate the proposed forward policy design and inverse reward learning algorithms in a navigation scenario. The results show that the behaviors of agents demonstrate both risk-averse and risk-seeking characteristics. Moreover, in the inverse reward learning task, the proposed bounded risk-sensitive inverse learning algorithm outperforms a baseline risk-neutral inverse learning algorithm by effectively recovering not only more accurate reward values but also the intelligence levels and the risk-measure parameters given demonstrations of agents' interactive behaviors.

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。

↑