English
Related papers

Related papers: Smoothing Policy Iteration for Zero-sum Markov Gam…

200 papers

In this paper, we consider the problem of optimization and learning for constrained and multi-objective Markov decision processes, for both discounted rewards and expected average rewards. We formulate the problems as zero-sum games where…

Optimization and Control · Mathematics 2021-03-05 Ather Gattami , Qinbo Bai , Vaneet Agarwal

In stochastic dynamic environments, team Markov games have emerged as a versatile paradigm for studying sequential decision-making problems of fully cooperative multi-agent systems. However, the optimality of the derived policies is usually…

Optimization and Control · Mathematics 2022-05-03 Feng Huang , Ming Cao , Long Wang

This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games. We focus on self-play algorithms which learn the optimal policy by playing against itself without any direct…

Machine Learning · Computer Science 2020-07-15 Yu Bai , Chi Jin , Tiancheng Yu

Model-based algorithms -- algorithms that explore the environment through building and utilizing an estimated model -- are widely used in reinforcement learning practice and theoretically shown to achieve optimal sample efficiency for…

Machine Learning · Computer Science 2021-02-09 Qinghua Liu , Tiancheng Yu , Yu Bai , Chi Jin

In single-agent Markov decision processes, an agent can optimize its policy based on the interaction with environment. In multi-player Markov games (MGs), however, the interaction is non-stationary due to the behaviors of other players, so…

Computer Science and Game Theory · Computer Science 2021-10-19 Yuanheng Zhu , Dongbin Zhao , Mengchen Zhao , Dong Li

This paper considers minimax optimization $\min_x \max_y f(x, y)$ in the challenging setting where $f$ can be both nonconvex in $x$ and nonconcave in $y$. Though such optimization problems arise in many machine learning paradigms including…

Machine Learning · Computer Science 2021-06-04 Tanner Fiez , Chi Jin , Praneeth Netrapalli , Lillian J. Ratliff

In this paper, we study the low-rank matrix minimization problem, where the loss function is convex but nonsmooth and the penalty term is defined by the cardinality function. We first introduce an exact continuous relaxation, that is, both…

Optimization and Control · Mathematics 2024-08-20 Quan Yu , Xinzhen Zhang

This paper considers the problem of inverse reinforcement learning in zero-sum stochastic games when expert demonstrations are known to be not optimal. Compared to previous works that decouple agents in the game by assuming optimality in…

Machine Learning · Statistics 2018-06-07 Xingyu Wang , Diego Klabjan

This paper introduces two metrics (cycle-based and memory-based metrics), grounded on a dynamical game-theoretic solution concept called sink equilibrium, for the evaluation, ranking, and computation of policies in multi-agent learning. We…

Computer Science and Game Theory · Computer Science 2020-06-23 Rui Yan , Xiaoming Duan , Zongying Shi , Yisheng Zhong , Jason R. Marden , Francesco Bullo

We consider a class of hierarchical noncooperative $N$-player games where the $i$th player solves a parametrized stochastic mathematical program with equilibrium constraints (MPEC) with the caveat that the implicit form of the $i$th…

Optimization and Control · Mathematics 2022-02-23 Shisheng Cui , Uday V. Shanbhag

Policy gradient methods have become a standard for training reinforcement learning agents in a scalable and efficient manner. However, they do not account for transition uncertainty, whereas learning robust policies can be computationally…

Machine Learning · Computer Science 2023-12-12 Navdeep Kumar , Esther Derman , Matthieu Geist , Kfir Levy , Shie Mannor

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…

Machine Learning · Computer Science 2020-06-15 Sriram Srinivasan , Marc Lanctot , Vinicius Zambaldi , Julien Perolat , Karl Tuyls , Remi Munos , Michael Bowling

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient methods. Convex Markov games, recently defined by Gemp et al.…

Computer Science and Game Theory · Computer Science 2025-06-23 Fivos Kalogiannis , Emmanouil-Vasileios Vlatakis-Gkaragkounis , Ian Gemp , Georgios Piliouras

The standard version of the policy iteration (PI) algorithm fails for semicontinuous models, that is, for models with lower semicontinuous one-step costs and weakly continuous transition law. This is due to the lack of continuity properties…

Optimization and Control · Mathematics 2023-07-17 Óscar Vega-Amaya , Fernando Luque-Vásquez

In this paper, we focus on finding the global minimizer of a general unconstrained nonsmooth nonconvex optimization problem. Taking advantage of the smoothing method and the consensus-based optimization (CBO) method, we propose a novel…

Optimization and Control · Mathematics 2025-01-14 Jiazhen Wei , Wei Bian

We propose policy gradient algorithms for solving a risk-sensitive reinforcement learning (RL) problem in on-policy as well as off-policy settings. We consider episodic Markov decision processes, and model the risk using the broad class of…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

Several works have shown unconditional hardness (via integrality gaps) of computing equilibria using strong hierarchies of convex relaxations. Such results however only apply to the problem of computing equilibria that optimize a certain…

Computational Complexity · Computer Science 2018-06-26 Pravesh K. Kothari , Ruta Mehta

The problem we consider is a multi-objective optimization problem, in which the goal is to find an optimal value of a vector function representing various criteria. The aim of this work is to develop an algorithm which utilizes the trust…

Optimization and Control · Mathematics 2026-05-15 Nataša Krejić , Nataša Krklec Jerinkić , Luka Rutešić

Existing studies on provably efficient algorithms for Markov games (MGs) almost exclusively build on the "optimism in the face of uncertainty" (OFU) principle. This work focuses on a different approach of posterior sampling, which is…

Machine Learning · Computer Science 2022-10-06 Wei Xiong , Han Zhong , Chengshuai Shi , Cong Shen , Tong Zhang

Recently discovered polyhedral structures of the value function for finite state-action discounted Markov decision processes (MDP) shed light on understanding the success of reinforcement learning. We investigate the value function polytope…

Machine Learning · Computer Science 2022-06-27 Yue Wu , Jesús A. De Loera