Credit assignment for collective multiagent RL with global rewards

• Main Authors: NGUYEN, Duc Thien, KUMAR, Akshat, LAU, Hoong Chuin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: Credit assignment methods; Decision-theoretic planning; Faster convergence; High-quality solutions; Multi-agent patrolling; Multi-agent planning; Partial observability; Real-world problem; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/4287; https://ink.library.smu.edu.sg/context/sis_research/article/5290/viewcontent/NIPS_2018_Credit_Assignment_For_Collective_Multiagent_RL.pdf
• Institution: Singapore Management University

Scaling decision theoretic planning to large multiagent systems is challenging due to uncertainty and partial observability in the environment. We focus on a multiagent planning model subclass, relevant to urban settings, where agent interactions are dependent on their collective influence'...