arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1207.1391cs.AI
收藏

风险敏感规划的存在性和唯一性条件:结果与猜想

Existence and Finiteness Conditions for Risk-Sensitive Planning: Results and Conjectures

University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Southern California(南加利福尼亚大学)

Yaxin Liu, Sven Koenig

摘要:

具有风险敏感规划目标的决策理论规划对于构建自主智能体或决策支持系统具有重要意义。然而,这条研究路线在很大程度上被人工智能和运筹学界所忽视,因为具有风险敏感规划目标的规划比具有风险中性规划目标的规划更复杂。为了弥补这种情况,我们推导出的条件,保证最佳的预期效用的总计划执行奖励存在和有限的完全可观察的马尔可夫决策过程模型的非线性效用函数。在具有正报酬和负报酬的马尔可夫决策过程模型中,我们的大多数结果只适用于平稳策略,但我们猜想它们可以推广到非平稳策略。

英文摘要:

Decision-theoretic planning with risk-sensitive planning objectives is important for building autonomous agents or decision-support systems for real-world applications. However, this line of research has been largely ignored in the artificial intelligence and operations research communities since planning with risk-sensitive planning objectives is more complicated than planning with risk-neutral planning objectives. To remedy this situation, we derive conditions that guarantee that the optimal expected utilities of the total plan-execution reward exist and are finite for fully observable Markov decision process models with non-linear utility functions. In case of Markov decision process models with both positive and negative rewards, most of our results hold for stationary policies only, but we conjecture that they can be generalized to non stationary policies.

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。

↑