Publications
For latest updates, please check my Google Scholar profile.
Published in Annual Reviews in Control, 2021
This review creates a taxonomy of MAL and establishes a unified and systematic way to understand multi-agent learning (MAL) from the perspective of information structures. In this article, we formally define the information structure in MAL, which quantitatively specifies the influence of the information on the learning process via belief generation. The proposed framework paves the way for a systematic discussion of the strengths and limitations of MAL algorithms under various information structures.
Published in arXiv, to appear in IEEE control system magazine, 2021
This article articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision making over networks. It highlights the strengths and challenges of adopting novel game-theoretic learning methods within the context of network systems.
Published in 55th Annual Conference on Information Sciences and Systems (CISS), 2021
This paper is about recasting markov decision process as an online linear optimization problem. Based on Blackwell approachability theory, a provably convergent no-regret learning algorithm is proposed
Published in arXiv, to appear in ACC, 2020
This paper is about a game framework to study constrained games on networks, where the players are locally aware of the constraints.
Published in arXiv, 2020
This paper is about a game-theoretic framework for distributed learning problems over networks, where nodes decide both the learning parameters and the network structure for communications.
Published in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), 2019
This paper is about adaptive linear function approximation in reinforcement leanring, which incorporates multi-resolution analysis and best M-term approximation
Published in Applied Mathematics Letters, 2018
This paper is about an interesting construction of directional framelets, which can be helpful in wavelet-based imaging