Jun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jun Li has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Huaqing Li
Southwest University
8 shared publications - Lianghao Ji
Chongqing University of Posts and Telecommunications
6 shared publications - Lifeng Zheng
Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China
6 shared publications - Liang Ran
Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China
5 shared publications - Zhe Li
College of Artificial Intelligence, Chongqing Business Vocational College, Chongqing 401331, China
3 shared publications - Cuijuan Zhang
Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China
2 shared publications
Latest Publications
- 17 March 2026
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 363 (7)
Bipartite consensus for heterogeneous multi-agent systems: A noncooperative game theoretic approach
- 17 March 2026
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 363 (7)
Bipartite consensus for heterogeneous multi-agent systems: A noncooperative game theoretic approach
- 4 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 14 (1) , 254-271
Distributed Generalized Aggregative Equilibrium Seeking via Inexact Krasnosel’skii-Mann Iteration Over Time-Varying Communication Graphs
This paper investigates the generalized aggregative equilibrium (GAE) under globally-shared affine coupling constraints within the context of aggregative games involving a collective of agents. Specifically, the study is centered on a non-smooth composite game scenario, wherein each agent possesses a local Lipschitz-differentiable function coupled with a lower semi-continuous function. Utilizing the operator splitting technique, the dynamic tracking method and the successive approximation theorem, we progressively formulate three GAE seeking algorithms from requiring full decision information to partial decision information. These algorithms leverage the local, time-varying communication framework and the deployment of splitting operators characterized by maximal monotone, alleviate the stringent requirement for strongly monotone. By employing the inexact Krasnosel'skii-Mann (KM) iteration and the aggregation invariance, we derive strict bounds on the non-vanishing iterative steps, establishing convergence toward the variational GAE (v-GAE). Finally, the effectiveness and superiority of the proposed algorithms are demonstrated through their application to the time-varying networked Nash-Cournot game model.
- 4 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 14 (1) , 254-271
Distributed Generalized Aggregative Equilibrium Seeking via Inexact Krasnosel’skii-Mann Iteration Over Time-Varying Communication Graphs
This paper investigates the generalized aggregative equilibrium (GAE) under globally-shared affine coupling constraints within the context of aggregative games involving a collective of agents. Specifically, the study is centered on a non-smooth composite game scenario, wherein each agent possesses a local Lipschitz-differentiable function coupled with a lower semi-continuous function. Utilizing the operator splitting technique, the dynamic tracking method and the successive approximation theorem, we progressively formulate three GAE seeking algorithms from requiring full decision information to partial decision information. These algorithms leverage the local, time-varying communication framework and the deployment of splitting operators characterized by maximal monotone, alleviate the stringent requirement for strongly monotone. By employing the inexact Krasnosel'skii-Mann (KM) iteration and the aggregation invariance, we derive strict bounds on the non-vanishing iterative steps, establishing convergence toward the variational GAE (v-GAE). Finally, the effectiveness and superiority of the proposed algorithms are demonstrated through their application to the time-varying networked Nash-Cournot game model.
- Open Access
- 13 January 2026
- Published by Scilight Press Pty Ltd in Journal of Machine Learning and Information Security
- Vol. 2 (1) , 1
Data-Based Optimal Couple-Group Consensus Control for Heterogeneous Multi-Agent Systems via Policy Gradient Reinforcement Learning
This paper investigates the optimal couple-group consensus control (OCGCC) for heterogeneous multi-agent systems (HeMASs) with completely unknown dynamics. The agents in HeMASs are divided into two groups according to order differences. Meanwhile, heterogeneous systems are transformed into homogeneous ones by adding virtual velocities. Then, a novel data-driven distributed control protocol for HeMASs is proposed based on policy gradient reinforcement learning (RL). The proposed algorithm is implemented asynchronously, and is specifically designed to address the issue of computational imbalance caused by individual differences among participants. It achieves this by constructing an actor-critic (AC) framework. The system’s learning efficacy is optimized using offline data sets. The convergence and stability are ensured by applying functional analysis and the Lyapunov stability theory. Finally, the effectiveness of the proposed algorithm is confirmed by various simulation examples.
- 13 January 2026
- Published by Scilight Press Pty Ltd in Journal of Machine Learning and Information Security
- Vol. 2 (1) , 1
Open AccessData-Based Optimal Couple-Group Consensus Control for Heterogeneous Multi-Agent Systems via Policy Gradient Reinforcement Learning
This paper investigates the optimal couple-group consensus control (OCGCC) for heterogeneous multi-agent systems (HeMASs) with completely unknown dynamics. The agents in HeMASs are divided into two groups according to order differences. Meanwhile, heterogeneous systems are transformed into homogeneous ones by adding virtual velocities. Then, a novel data-driven distributed control protocol for HeMASs is proposed based on policy gradient reinforcement learning (RL). The proposed algorithm is implemented asynchronously, and is specifically designed to address the issue of computational imbalance caused by individual differences among participants. It achieves this by constructing an actor-critic (AC) framework. The system’s learning efficacy is optimized using offline data sets. The convergence and stability are ensured by applying functional analysis and the Lyapunov stability theory. Finally, the effectiveness of the proposed algorithm is confirmed by various simulation examples.
- 9 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (2) , 1595-1609
Asynchronous Distributed Nonsmooth Composite Optimization via Computation-Efficient Primal-Dual Proximal Algorithms
This paper focuses on a distributed nonsmooth composite optimization problem over a multiagent networked system, in which each agent is equipped with a local Lipschitz-differentiable function and two possibly nonsmooth functions, one of which incorporates a linear mapping. To address this problem, we introduce a synchronous distributed algorithm featuring uncoordinated relaxed factors. It serves as a generalized relaxed version of the recent method TriPD-Dist. Notably, the considered problem in the presence of asynchrony and delays remains relatively unexplored. In response, a new asynchronous distributed primal-dual proximal algorithm is first proposed, rooted in a comprehensive asynchronous model. It is operated under the assumption that agents utilize possibly outdated information from their neighbors, while considering arbitrary, time-varying, yet bounded delays. With some special adjustments, new asynchronous distributed extensions of existing centralized methods are obtained via the proposed asynchronous algorithm. Theoretically, a new convergence analysis technique of the proposed algorithms is provided. Specifically, a sublinear convergence rate is explicitly derived by showcasing that the iteration behaves as a nonexpansive operator. In addition, the proposed asynchronous algorithm converges the optimal solution in expectation under the same step-size conditions as its synchronous counterpart. Finally, numerical studies substantiate the efficacy of the proposed algorithms and validate their performance in practical scenarios.
- 9 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (2) , 1595-1609
Asynchronous Distributed Nonsmooth Composite Optimization via Computation-Efficient Primal-Dual Proximal Algorithms
This paper focuses on a distributed nonsmooth composite optimization problem over a multiagent networked system, in which each agent is equipped with a local Lipschitz-differentiable function and two possibly nonsmooth functions, one of which incorporates a linear mapping. To address this problem, we introduce a synchronous distributed algorithm featuring uncoordinated relaxed factors. It serves as a generalized relaxed version of the recent method TriPD-Dist. Notably, the considered problem in the presence of asynchrony and delays remains relatively unexplored. In response, a new asynchronous distributed primal-dual proximal algorithm is first proposed, rooted in a comprehensive asynchronous model. It is operated under the assumption that agents utilize possibly outdated information from their neighbors, while considering arbitrary, time-varying, yet bounded delays. With some special adjustments, new asynchronous distributed extensions of existing centralized methods are obtained via the proposed asynchronous algorithm. Theoretically, a new convergence analysis technique of the proposed algorithms is provided. Specifically, a sublinear convergence rate is explicitly derived by showcasing that the iteration behaves as a nonexpansive operator. In addition, the proposed asynchronous algorithm converges the optimal solution in expectation under the same step-size conditions as its synchronous counterpart. Finally, numerical studies substantiate the efficacy of the proposed algorithms and validate their performance in practical scenarios.
- 6 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (1) , 642-648
Convergence Analysis of Distributed Generalized Nash Equilibria Seeking Algorithm With Asynchrony and Delays
This paper considers a class of noncooperative games in which the feasible decision sets of all players are coupled together by a coupled inequality constraint. Adopting the variational inequality formulation of the game, we first introduce a new local edge-based equilibrium condition with full information. Considering challenges when communication delays occur, we then devise an asynchronous distributed algorithm to seek a generalized Nash equilibrium. This asynchronous scheme arbitrarily activates one player to start new computations independently at different iteration instants, which means that the picked player can use the involved out-dated information from itself and its neighbors to perform new updates. In theoretical aspect, we provide explicit conditions on algorithm parameters, for instance, the step-sizes to establish a sublinear convergence rate for the synchronous version. Next, the asynchronous algorithm guarantees almost sure convergence in expectation under the same step-size conditions and some standard assumptions. Finally, the viability and performance of the proposed algorithm are demonstrated by numerical studies on the Cournot competition.
- 6 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (1) , 642-648
Convergence Analysis of Distributed Generalized Nash Equilibria Seeking Algorithm With Asynchrony and Delays
This paper considers a class of noncooperative games in which the feasible decision sets of all players are coupled together by a coupled inequality constraint. Adopting the variational inequality formulation of the game, we first introduce a new local edge-based equilibrium condition with full information. Considering challenges when communication delays occur, we then devise an asynchronous distributed algorithm to seek a generalized Nash equilibrium. This asynchronous scheme arbitrarily activates one player to start new computations independently at different iteration instants, which means that the picked player can use the involved out-dated information from itself and its neighbors to perform new updates. In theoretical aspect, we provide explicit conditions on algorithm parameters, for instance, the step-sizes to establish a sublinear convergence rate for the synchronous version. Next, the asynchronous algorithm guarantees almost sure convergence in expectation under the same step-size conditions and some standard assumptions. Finally, the viability and performance of the proposed algorithm are demonstrated by numerical studies on the Cournot competition.
- 6 July 2024
- Published by Elsevier in Neurocomputing
- Vol. 600
Action-dependent heuristic dynamic programming for hybrid-order systems based on dynamic event-triggered mechanism
- 6 July 2024
- Published by Elsevier in Neurocomputing
- Vol. 600
Action-dependent heuristic dynamic programming for hybrid-order systems based on dynamic event-triggered mechanism
- 24 April 2024
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 112 (12) , 10095-10108
Time-varying formation optimization tracking of multi-agent systems with semi-Markov switching topology
- 24 April 2024
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 112 (12) , 10095-10108
Time-varying formation optimization tracking of multi-agent systems with semi-Markov switching topology
- 9 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 10, 179-194
Distributed Generalized Nash Equilibria Computation of Noncooperative Games Via Novel Primal-Dual Splitting Algorithms
This paper investigates the generalized Nash equilibria (GNE) seeking problem for noncooperative games, where all players dedicate to selfishly minimizing their own cost functions subject to local constraints and coupled constraints. To tackle the considered problem, we initially form an explicit local equilibrium condition for its variational formulation. By employing proximal splitting operators, a novel distributed primal-dual splitting algorithm with full-decision information (Dist_PDS_FuDeIn) is designed, eliminating the need for global step-sizes. Furthermore, to address scenarios where players lack access to all other players' decisions, a local estimation is introduced to approximate the decision information of other players, and a fully distributed primal-dual splitting algorithm with partial-decision information (Dist_PDS_PaDeIn) is then proposed. Both algorithms enable the derivation of new distributed forward-backward-like extensions. Theoretically, a new analytical approach for convergence is presented, demonstrating that the proposed algorithms converge to the variational GNE of games, and their convergence rates are also proven, provided that uncoordinated step-sizes are positive and less than explicit upper bounds. Moreover, the approach not only generalizes the forward-backward splitting technique but also improves convergence rates of several well-known algorithms. Finally, the advantages of Dist_PDS_FuDeIn and Dist_PDS_PaDeIn are illustrated through comparative simulations.
- 9 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 10, 179-194
Distributed Generalized Nash Equilibria Computation of Noncooperative Games Via Novel Primal-Dual Splitting Algorithms
This paper investigates the generalized Nash equilibria (GNE) seeking problem for noncooperative games, where all players dedicate to selfishly minimizing their own cost functions subject to local constraints and coupled constraints. To tackle the considered problem, we initially form an explicit local equilibrium condition for its variational formulation. By employing proximal splitting operators, a novel distributed primal-dual splitting algorithm with full-decision information (Dist_PDS_FuDeIn) is designed, eliminating the need for global step-sizes. Furthermore, to address scenarios where players lack access to all other players' decisions, a local estimation is introduced to approximate the decision information of other players, and a fully distributed primal-dual splitting algorithm with partial-decision information (Dist_PDS_PaDeIn) is then proposed. Both algorithms enable the derivation of new distributed forward-backward-like extensions. Theoretically, a new analytical approach for convergence is presented, demonstrating that the proposed algorithms converge to the variational GNE of games, and their convergence rates are also proven, provided that uncoordinated step-sizes are positive and less than explicit upper bounds. Moreover, the approach not only generalizes the forward-backward splitting technique but also improves convergence rates of several well-known algorithms. Finally, the advantages of Dist_PDS_FuDeIn and Dist_PDS_PaDeIn are illustrated through comparative simulations.
- Open Access
- 12 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Cyber-Physical Systems
- Vol. 1, 123-135
Model-Free Reinforcement Learning Economic Dispatch Algorithms for Price-Based Residential Demand Response Management System
It is projected that plug-in electric vehicles (PEVs) would steadily increase as household appliances. However, PEVs' high power consumption, stochastic usage patterns, and storage capacity will surely result in a rise in the elasticity of demand response and pose significant difficulties for price-based residential demand response management (PRDRM). This paper aims to optimize a two-tier globally shared nonconvex PRDRM problem with local constraints and PEVs, known as social welfare: maximizing retailer profits and minimizing the combined residential costs. This is done by balancing residential electricity use with retail electricity prices in an unknown market environment. The proposed online/offline model-free reinforcement learning-based economic dispatch (MFRL-ED) methods can adaptively decide on the ideal retail price sequence by integrating the daily residential-retailer behavior model with the agent-environment interaction method, providing a basic MFRL-ED solution for PRDRM without a system identification step and an accurate load-retail model. Experiments show that MFRL-ED methods provide an effective class of PRDRM solutions.
- 12 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Cyber-Physical Systems
- Vol. 1, 123-135
Open AccessModel-Free Reinforcement Learning Economic Dispatch Algorithms for Price-Based Residential Demand Response Management System
It is projected that plug-in electric vehicles (PEVs) would steadily increase as household appliances. However, PEVs' high power consumption, stochastic usage patterns, and storage capacity will surely result in a rise in the elasticity of demand response and pose significant difficulties for price-based residential demand response management (PRDRM). This paper aims to optimize a two-tier globally shared nonconvex PRDRM problem with local constraints and PEVs, known as social welfare: maximizing retailer profits and minimizing the combined residential costs. This is done by balancing residential electricity use with retail electricity prices in an unknown market environment. The proposed online/offline model-free reinforcement learning-based economic dispatch (MFRL-ED) methods can adaptively decide on the ideal retail price sequence by integrating the daily residential-retailer behavior model with the agent-environment interaction method, providing a basic MFRL-ED solution for PRDRM without a system identification step and an accurate load-retail model. Experiments show that MFRL-ED methods provide an effective class of PRDRM solutions.
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 360-365
A Novel Distributed Algorithm to Seek GNE for Aggregative Games via Primal-Dual Proximal Gradient
In this paper, the generalized Nash equilibria (GNE) problems over the aggregative game is concerned inspired by the widely application of non-cooperative game in many fields. In the game, each agent aims to minimize its own objective function that depends on both its private decision and the average decision information of all agents’. Furthermore, decision variables are within feasible decision sets and shares a global coupling inequality constraint. To seek the GNE, a novel distributed primal-dual proximal algorithm is proposed. Meanwhile, the proposed algorithm adopts edge-based communication model and takes uncoordinated step-sizes that avoid the conservativeness. By the theories of monotone inclusion and averaged operators, convergence of the algorithm is proved. Finally, numerical studies on electric vehicles path and destination strategy problem are conducted to clarify the efficiency of the proposed algorithm.
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 360-365
A Novel Distributed Algorithm to Seek GNE for Aggregative Games via Primal-Dual Proximal Gradient
In this paper, the generalized Nash equilibria (GNE) problems over the aggregative game is concerned inspired by the widely application of non-cooperative game in many fields. In the game, each agent aims to minimize its own objective function that depends on both its private decision and the average decision information of all agents’. Furthermore, decision variables are within feasible decision sets and shares a global coupling inequality constraint. To seek the GNE, a novel distributed primal-dual proximal algorithm is proposed. Meanwhile, the proposed algorithm adopts edge-based communication model and takes uncoordinated step-sizes that avoid the conservativeness. By the theories of monotone inclusion and averaged operators, convergence of the algorithm is proved. Finally, numerical studies on electric vehicles path and destination strategy problem are conducted to clarify the efficiency of the proposed algorithm.