18217081. BILEVEL DECENTRALIZED MULTI-AGENT LEARNING (International Business Machines Corporation)

BILEVEL DECENTRALIZED MULTI-AGENT LEARNING

Organization Name

International Business Machines Corporation

Inventor(s)

Siliang Zeng of Minneapolis MN (US)

Songtao Lu of White Plains NY (US)

Xiaodong Cui of Chappaqua NY (US)

Mark S. Squillante of Greenwich CT (US)

Lior Horesh of North Salem NY (US)

Brian E. D. Kingsbury of Cortlandt Manor NY (US)

Mingyi Hong of Wayzata MN (US)

BILEVEL DECENTRALIZED MULTI-AGENT LEARNING

This abstract first appeared for US patent application 18217081 titled 'BILEVEL DECENTRALIZED MULTI-AGENT LEARNING

Original Abstract Submitted

A computer-implemented method of decentralized multi-agent learning for use in a system having a plurality of intelligent agents each having a personal portion and a shared portion, is provided. The method includes iteratively, until each of a personal goal and a network goal are optimized: determining a feedback associated with an action relative to a personal goal and a degree of similarity relative to a shared goal; adjusting a policy based on the feedback to gain a superior feedback from a next action; broadcasting the shared policy; receiving the at least one of the one or more other intelligent agents' shared policy; generating a combined policy by combining the personal policy and the at least one of the one or more other intelligent agents' shared policy; estimating, using the combined policy, a network value function; and conducting the next action in accordance with the combined policy.