Seminars
View all Seminars | Download ICal for this eventA decentralised algorithm for minimizing multi-agent congestion cost on a network
Series: Department Seminar
Speaker: Prof. N. Hemachandra Industrial Engineering and Operations Research Indian Institute of Technology Bombay
Date/Time: Mar 03 11:00:00
Location: CSA Seminar Hall (Room No. 254, First Floor)
Abstract:
Consider a model wherein a given set of agents need to reach the goal node of a network. The cost for each agent on any link depends on the congestion on that link as well as on a cost component that is private to that agent. We propose a multi-agent congestion cost minimization (MACCM) algorithm for minimizing the total cost incurred by the agents. Our algorithm is fully decentralised, uses linear function approximations that addresses privacy of agents costs as well as scalability aspects and achieves sub-linear regret. Each agent maintains an estimate of the global objective function and the algorithm relies on a multi-agent version of extended value-iteration. We illustrate computations on a hard instance. Our model is a generalisation of a classical learning problem, the stochastic shortest path problem. This is a joint work with Prashant Trivedi.
Speaker Bio:
N. Hemachandra is a Professor at Industrial Engineering and Operations Research, IIT Bombay. His academic interests are learning algorithms, sequential decision models including RL, MABs, and Markov decision models, queueing theory, game theory, etc. and their applications to pricing and resource allocation problems arising in supply and value chains, communication networks, logistics, etc.
Host Faculty: Dr. Gugan Thoppe