Decentralized planning in stochastic environments with submodular rewards

• Main Authors: KUMAR, Rajiv Ranjan, Pradeep VARAKANTHAM, Akshat KUMAR
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2017
• 主題: Multiagent Systems; Planning under uncertainty; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/3549; https://ink.library.smu.edu.sg/context/sis_research/article/4550/viewcontent/14928_66557_1_PB.pdf

Decentralized Markov Decision Process (Dec-MDP) providesa rich framework to represent cooperative decentralizedand stochastic planning problems under transition uncertainty.However, solving a Dec-MDP to generate coordinatedyet decentralized policies is NEXP-Hard. Researchershave made significant pro...