Yi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yi Zhang has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Alexey Piunovskiy
University of Liverpool
22 shared publications - Xin Guo
School of Science Sun Yat-sen University 510275 Guangzhou China
11 shared publications Alexey Piunovskiy
10 shared publications- Konstantin Avrachenkov
Inria, Université Côte d’Azur
9 shared publications - Alexey Piunovskiy
University of Liverpool
6 shared publications Xianping Guo
6 shared publications
Latest Publications
- Open Access
- 1 January 2027
- Published by Banach Press LLC in Journal of Convex Analysis
- Vol. 34 (1) , 471-503
Primal-Dual Programs for the Constrained Optimal Impulse Control: Discounted Model
This paper studies constrained optimal impulse control problems of a deterministic system described by a (semi)flow, where the performance measures are the discounted total costs including both the costs incurred with applying impulses as well as running costs. We formulate the relaxed problem and the associated primal convex programs in measures together with the dual programs, and establish the relevant duality results. As an application, we formulate and justify a general procedure for obtaining optimal (J+1) ( J + 1 ) -mixed strategies for the original impulse control problems. This procedure is illustrated with an explicitly solved example.
- 1 January 2027
- Published by Banach Press LLC in Journal of Convex Analysis
- Vol. 34 (1) , 471-503
Open AccessPrimal-Dual Programs for the Constrained Optimal Impulse Control: Discounted Model
This paper studies constrained optimal impulse control problems of a deterministic system described by a (semi)flow, where the performance measures are the discounted total costs including both the costs incurred with applying impulses as well as running costs. We formulate the relaxed problem and the associated primal convex programs in measures together with the dual programs, and establish the relevant duality results. As an application, we formulate and justify a general procedure for obtaining optimal (J+1) ( J + 1 ) -mixed strategies for the original impulse control problems. This procedure is illustrated with an explicitly solved example.
- Open Access
- 21 January 2026
- Published by Elsevier in Operations Research Letters
- Vol. 65
On stochastic non-linear discounting
- 21 January 2026
- Published by Elsevier in Operations Research Letters
- Vol. 65
Open AccessOn stochastic non-linear discounting
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- p. 1-12
On Safety-Constrained Markov Decision Processes
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- p. 1-12
On Safety-Constrained Markov Decision Processes
- 1 November 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 50 (4) , 2552-2576
On Average Optimality for Non-Stationary Markov Decision Processes in Borel Spaces
This paper studies Borel models of nonstationary Markov decision processes (MDPs) with average criteria. We establish a suitable fixed point theorem, which is used to show the existence of solutions to the average optimality equation (AOE), without using contractions. The existence of optimal policies follows from the obtained solutions to the AOE. Furthermore, we show that versions of the rolling horizon algorithm can be used to produce an optimal policy or an ϵ-optimal policy. Finally, we compare the optimality conditions imposed in this paper with the existing ones in the literature, and demonstrate that they can be satisfied while the previous ones are not. Funding: This research was supported by National Key Research and Development Program of China [2022YFA1004600], National Natural Science Foundation of China [No. 12301170], Guangdong Basic and Applied Research Foundation [2023A1515012644], and the Fundamental Research Funds for the Central Universities, Sun Yat-Sen University [No. 23qnpy39].
- 1 November 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 50 (4) , 2552-2576
On Average Optimality for Non-Stationary Markov Decision Processes in Borel Spaces
This paper studies Borel models of nonstationary Markov decision processes (MDPs) with average criteria. We establish a suitable fixed point theorem, which is used to show the existence of solutions to the average optimality equation (AOE), without using contractions. The existence of optimal policies follows from the obtained solutions to the AOE. Furthermore, we show that versions of the rolling horizon algorithm can be used to produce an optimal policy or an ϵ-optimal policy. Finally, we compare the optimality conditions imposed in this paper with the existing ones in the literature, and demonstrate that they can be satisfied while the previous ones are not. Funding: This research was supported by National Key Research and Development Program of China [2022YFA1004600], National Natural Science Foundation of China [No. 12301170], Guangdong Basic and Applied Research Foundation [2023A1515012644], and the Fundamental Research Funds for the Central Universities, Sun Yat-Sen University [No. 23qnpy39].
- Open Access
Primal-dual programs for the constrained optimal impulse control: discounted model
This paper studies constrained optimal impulse control problems of a deterministic system described by a (semi)flow, where the performance measures are the discounted total costs including both the costs incurred with applying impulses as well as running costs. We formulate the relaxed problem and the associated primal convex programs in measures together with the dual programs, and establish the relevant duality results. As an application, we formulate and justify a general procedure for obtaining optimal $(J+1)$-mixed strategies for the original impulse control problems. This procedure is illustrated with a solved example.
Open AccessPrimal-dual programs for the constrained optimal impulse control: discounted model
This paper studies constrained optimal impulse control problems of a deterministic system described by a (semi)flow, where the performance measures are the discounted total costs including both the costs incurred with applying impulses as well as running costs. We formulate the relaxed problem and the associated primal convex programs in measures together with the dual programs, and establish the relevant duality results. As an application, we formulate and justify a general procedure for obtaining optimal $(J+1)$-mixed strategies for the original impulse control problems. This procedure is illustrated with a solved example.
- Open Access
- 11 March 2025
- Published by Springer Nature in Annals of Operations Research
Reduction of a Markov decision process with non-linear discounting to a stochastic game with standard total undiscounted criterion
We consider a Markov decision process (MDP), whose total discounted utility is aggregated recursively with a concave discount function that is not necessarily linear. The state and action spaces are Borel spaces, and the utility function is nonnegative. We show that it can be reduced to a turn-based stochastic game model with the total undiscounted utility. This reduction result is then applied to the MDP problem with recursively aggregated utility to be maximized or cost to be minimized.
- 11 March 2025
- Published by Springer Nature in Annals of Operations Research
Open AccessReduction of a Markov decision process with non-linear discounting to a stochastic game with standard total undiscounted criterion
We consider a Markov decision process (MDP), whose total discounted utility is aggregated recursively with a concave discount function that is not necessarily linear. The state and action spaces are Borel spaces, and the utility function is nonnegative. We show that it can be reduced to a turn-based stochastic game model with the total undiscounted utility. This reduction result is then applied to the MDP problem with recursively aggregated utility to be maximized or cost to be minimized.
- Open Access
- 24 September 2024
- Published by Elsevier in Operations Research Letters
- Vol. 57
Further remarks on absorbing Markov decision processes
- 24 September 2024
- Published by Elsevier in Operations Research Letters
- Vol. 57
Open AccessFurther remarks on absorbing Markov decision processes
- Open Access
- 12 April 2024
- Published by Springer Nature in Applied Mathematics & Optimization
- Vol. 89 (3) , 1-25
On the Continuity of the Projection Mapping from Strategic Measures to Occupation Measures in Absorbing Markov Decision Processes
In this paper, we prove the following assertion for an absorbing Markov decision process (MDP) with the given initial distribution, which is also assumed to be semi-continuous: the continuity of the projection mapping from the space of strategic measures to the space of occupation measures, both endowed with their weak topologies, is equivalent to the MDP model being uniformly absorbing. An example demonstrates, among other interesting scenarios, that for an absorbing (but not uniformly absorbing) semi-continuous MDP with the given initial distribution, the space of occupation measures can fail to be compact in the weak topology.
- 12 April 2024
- Published by Springer Nature in Applied Mathematics & Optimization
- Vol. 89 (3) , 1-25
Open AccessOn the Continuity of the Projection Mapping from Strategic Measures to Occupation Measures in Absorbing Markov Decision Processes
In this paper, we prove the following assertion for an absorbing Markov decision process (MDP) with the given initial distribution, which is also assumed to be semi-continuous: the continuity of the projection mapping from the space of strategic measures to the space of occupation measures, both endowed with their weak topologies, is equivalent to the MDP model being uniformly absorbing. An example demonstrates, among other interesting scenarios, that for an absorbing (but not uniformly absorbing) semi-continuous MDP with the given initial distribution, the space of occupation measures can fail to be compact in the weak topology.
- 12 January 2024
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Control and Optimization
- Vol. 62 (1) , 65-90
Extreme Occupation Measures in Markov Decision Processes with an Absorbing State
In this paper, we consider a Markov decision process (MDP) with a Borel state space [Formula: see text], where [Formula: see text] is an absorbing state (cemetery), and a Borel action space [Formula: see text]. We consider the space of finite occupation measures restricted on [Formula: see text] and the extreme points in it. It is possible that some strategies have infinite occupation measures. Nevertheless, we prove that every finite extreme occupation measure is generated by a deterministic stationary strategy. Then, for this MDP, we consider a constrained problem with total undiscounted criteria and [Formula: see text] constraints, where the cost functions are nonnegative. By assumption, the strategies inducing infinite occupation measures are not optimal. Then our second main result is that, under mild conditions, the solution to this constrained MDP is given by a mixture of no more than [Formula: see text] occupation measures generated by deterministic stationary strategies.
- 12 January 2024
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Control and Optimization
- Vol. 62 (1) , 65-90
Extreme Occupation Measures in Markov Decision Processes with an Absorbing State
In this paper, we consider a Markov decision process (MDP) with a Borel state space [Formula: see text], where [Formula: see text] is an absorbing state (cemetery), and a Borel action space [Formula: see text]. We consider the space of finite occupation measures restricted on [Formula: see text] and the extreme points in it. It is possible that some strategies have infinite occupation measures. Nevertheless, we prove that every finite extreme occupation measure is generated by a deterministic stationary strategy. Then, for this MDP, we consider a constrained problem with total undiscounted criteria and [Formula: see text] constraints, where the cost functions are nonnegative. By assumption, the strategies inducing infinite occupation measures are not optimal. Then our second main result is that, under mild conditions, the solution to this constrained MDP is given by a mixture of no more than [Formula: see text] occupation measures generated by deterministic stationary strategies.