English
Related papers

Related papers: Last-Iterate Convergent Policy Gradient Primal-Dua…

200 papers

The robust constrained Markov decision process (RCMDP) is a recent task-modelling framework for reinforcement learning that incorporates behavioural constraints and that provides robustness to errors in the transition dynamics model through…

Machine Learning · Computer Science 2024-05-16 David M. Bossens

Trajectory optimization is an efficient approach for solving optimal control problems for complex robotic systems. It relies on two key components: first the transcription into a sparse nonlinear program, and second the corresponding solver…

Robotics · Computer Science 2022-10-31 Wilson Jallet , Antoine Bambade , Nicolas Mansard , Justin Carpentier

We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…

Machine Learning · Computer Science 2023-06-02 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard…

Machine Learning · Computer Science 2022-10-19 Ruida Zhou , Tao Liu , Dileep Kalathil , P. R. Kumar , Chao Tian

In this paper, we consider a class of finite-sum convex optimization problems whose objective function is given by the summation of $m$ ($\ge 1$) smooth components together with some other relatively simple terms. We first introduce a…

Optimization and Control · Mathematics 2015-10-27 Guanghui Lan , Yi Zhou

We study the problem of computing an optimal large language model (LLM) policy for the constrained alignment problem, where the goal is to maximize a primary reward objective while satisfying constraints on secondary utilities. Despite the…

Machine Learning · Computer Science 2025-11-27 Botong Zhang , Shuo Li , Ignacio Hounie , Osbert Bastani , Dongsheng Ding , Alejandro Ribeiro

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

We study entropy-regularized constrained Markov decision processes (CMDPs) under the soft-max parameterization, in which an agent aims to maximize the entropy-regularized value function while satisfying constraints on the expected total…

Machine Learning · Computer Science 2023-04-10 Donghao Ying , Yuhao Ding , Javad Lavaei

In this paper, a projected primal-dual gradient flow of augmented Lagrangian is presented to solve convex optimization problems that are not necessarily strictly convex. The optimization variables are restricted by a convex set with…

Optimization and Control · Mathematics 2018-10-31 Han Zhang , Jieqiang Wei , Peng Yi , Xiaoming Hu

Designing a safe policy for uncertain environments is crucial in real-world control systems. However, this challenge remains inadequately addressed within the Markov decision process (MDP) framework. This paper presents the first algorithm…

We study the setting of \emph{performative reinforcement learning} where the deployed policy affects both the reward, and the transition of the underlying Markov decision process. Prior work~\parencite{MTR23} has addressed this problem…

Machine Learning · Computer Science 2025-03-18 Debmalya Mandal , Goran Radanovic

We consider discounted infinite-horizon constrained Markov decision processes (CMDPs), where the goal is to find an optimal policy that maximizes the expected cumulative reward while satisfying expected cumulative constraints. Motivated by…

Machine Learning · Computer Science 2025-03-04 Tingting Ni , Maryam Kamgarpour

We study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a…

Machine Learning · Statistics 2016-12-09 Yichen Chen , Mengdi Wang

Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications, where decisions must optimize cumulative rewards while strictly adhering to complex nonlinear constraints. In domains such as power systems,…

Machine Learning · Computer Science 2025-02-21 Andrew Rosemberg , Alexandre Street , Davi M. Valladão , Pascal Van Hentenryck

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision…

Machine Learning · Computer Science 2020-10-13 Reazul Hasan Russel , Mouhacine Benosman , Jeroen Van Baar

Several well-known algorithms in the field of combinatorial optimization can be interpreted in terms of the primal-dual method for solving linear programs. For example, Dijkstra's algorithm, the Ford-Fulkerson algorithm, and the Hungarian…

Optimization and Control · Mathematics 2016-01-19 Randy Cogill

Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under…

Machine Learning · Computer Science 2025-12-19 David M. Bossens , Atsushi Nitanda

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (minimize…

Optimization and Control · Mathematics 2015-07-08 Mahmoud El Chamie , Behcet Acikmese

Recently there has been an increasing interest in primal-dual methods for model predictive control (MPC), which require minimizing the (augmented) Lagrangian at each iteration. We propose a novel first order primal-dual method, termed…

Optimization and Control · Mathematics 2020-12-21 Yue Yu , Purnanand Elango , Behçet Açikmeşe

Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empirical success, a rigorous understanding of the global…

Optimization and Control · Mathematics 2020-06-30 Kaiqing Zhang , Alec Koppel , Hao Zhu , Tamer Başar