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 1407.7191cs.AI
收藏

无意识的MDP

MDPs with Unawareness

Cornell University(康奈尔大学)

Joseph Y. Halpern, Nan Rong, Ashutosh Saxena

摘要:

马尔可夫决策过程(MDP)被广泛用于机器人、自动控制和经济学中的决策问题建模。传统的MDP假设决策者(DM)知道所有的状态和动作。然而,在许多感兴趣的情况下,这可能不是真的。我们定义了一个新的框架,MDPs与无意识(MDPU)处理的可能性,DM可能不知道所有可能的行动。我们提供了一个完整的表征时,DM可以学习发挥近最佳的MDPU,并给出了一个算法,学习发挥近最佳时,它是可能的,尽可能有效。特别是,我们的特点时,可以找到一个接近最优的解决方案在多项式时间。

英文摘要:

Markov decision processes (MDPs) are widely used for modeling decision-making problems in robotics, automated control, and economics. Traditional MDPs assume that the decision maker (DM) knows all states and actions. However, this may not be true in many situations of interest. We define a new framework, MDPs with unawareness (MDPUs) to deal with the possibilities that a DM may not be aware of all possible actions. We provide a complete characterization of when a DM can learn to play near-optimally in an MDPU, and give an algorithm that learns to play near-optimally when it is possible to do so, as efficiently as possible. In particular, we characterize when a near-optimal solution can be found in polynomial time.

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。

↑