Certified policy verification and synthesis for MDPs under distributional reach-avoidance properties

• Main Authors: AKSHAY, S., CHATTERJEE, Krishnendu, MEGGENDORFER, Tobias, ZIKELIC, Dorde
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Agent-based and Multi-agent Systems: MAS: Formal verification; validation and synthesis; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/9340; https://ink.library.smu.edu.sg/context/sis_research/article/10340/viewcontent/0001.pdf
• Institution: Singapore Management University

Markov Decision Processes (MDPs) are a classical model for decision making in the presence of uncertainty. Often they are viewed as state transformers with planning objectives defined with respect to paths over MDP states. An increasingly popular alternative is to view them as distribution transform...