no code implementations • 21 Apr 2024 • Yaqun Yang, Jinlong Lei
To address the special optimization problem, we propose a coupled distributed stochastic approximation algorithm, in which every agent updates the current beliefs of its unknown parameter and decision variable by stochastic approximation method; and then averages the beliefs and decision variables of its neighbors over network in consensus protocol.
no code implementations • 17 Apr 2024 • Yaqun Yang, Jinlong Lei, Guanghui Wen, Yiguang Hong
This paper considers a distributed adaptive optimization problem, where all agents only have access to their local cost functions with a common unknown parameter, whereas they mean to collaboratively estimate the true parameter and find the optimal solution over a connected network.
no code implementations • 14 Oct 2023 • Jianguo Chen, Jinlong Lei, HongSheng Qi, Yiguang Hong
This work studies the parameter identification problem of a generalized non-cooperative game, where each player's cost function is influenced by an observable signal and some unknown parameters.
no code implementations • 14 May 2022 • Wenting Liu, Jinlong Lei, Peng Yi, Yiguang Hong
This paper considers no-regret learning for repeated continuous-kernel games with lossy bandit feedback.
no code implementations • 25 Nov 2021 • Xiaoxiao Zhao, Jinlong Lei, Li Li, Jie Chen
This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.
Multi-agent Reinforcement Learning reinforcement-learning +2
no code implementations • NeurIPS 2020 • Jinlong Lei, Peng Yi, Yiguang Hong, Jie Chen, Guodong Shi
The regret bounds scaling with respect to $T$ match those obtained by state-of-the-art algorithms and fundamental limits in the corresponding centralized online optimization problems, e. g., $\mathcal{O}(\sqrt{T}) $ and $\mathcal{O}(\ln(T)) $ regrets are established for convex and strongly convex losses with full gradient feedback and two-points information, respectively.