Solving Uncertain MDPs with Objectives that are Separable over Instantiations of Model Uncertainty

• Main Authors: ADULYASAK, Yossiri, VARAKANTHAM, Pradeep, AHMED, Asrar, JAILLET, Patrick
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2015
• 主題: Markov Decision Problems (MDPs); Lagrangian Dual Decomposition; Bayesian Reinforcement Learning; Robust MDPs; Artificial Intelligence and Robotics; Computer Sciences; Numerical Analysis and Scientific Computing
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/2916; https://ink.library.smu.edu.sg/context/sis_research/article/3916/viewcontent/9843_44958_1_PB.pdf

Markov Decision Problems, MDPs offer an effective mechanism for planning under uncertainty. However, due to unavoidable uncertainty over models, it is difficult to obtain an exact specification of an MDP. We are interested in solving MDPs, where transition and reward functions are not exactly specif...