English
Related papers

Related papers: Decentralized Optimistic Hyperpolicy Mirror Descen…

200 papers

We study the policy testing problem in discounted Markov decision processes (MDPs) in the fixed-confidence setting under a generative model with static sampling. The goal is to decide whether the value of a given policy exceeds a specified…

Machine Learning · Statistics 2026-04-21 Kaito Ariu , Po-An Wang , Alexandre Proutiere , Kenshi Abe

Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed that if all agents in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights Update (OMWU), the external regret of every player is…

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central…

Optimization and Control · Mathematics 2022-11-01 Runyu Zhang , Jincheng Mei , Bo Dai , Dale Schuurmans , Na Li

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

Machine Learning · Computer Science 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous…

Optimization and Control · Mathematics 2022-03-01 Daniil Tiapkin , Alexander Gasnikov

Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning (MARL). One of the reasons is the policy changes of agents during the learning process. Some existing works have discussed various consequences caused by…

Machine Learning · Computer Science 2022-02-11 Wenhao Li , Xiangfeng Wang , Bo Jin , Junjie Sheng , Hongyuan Zha

Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and…

Machine Learning · Computer Science 2015-03-17 Stephane Ross , Geoffrey J. Gordon , J. Andrew Bagnell

In this paper we study two-player bilinear zero-sum games with constrained strategy spaces. An instance of natural occurrences of such constraints is when mixed strategies are used, which correspond to a probability simplex constraint. We…

Computer Science and Game Theory · Computer Science 2022-06-10 Andre Wibisono , Molei Tao , Georgios Piliouras

Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works,…

Machine Learning · Computer Science 2021-10-26 Soumya Rani Samineni

We study the problem of \emph{dynamic regret minimization} in $K$-armed Dueling Bandits under non-stationary or time varying preferences. This is an online learning setup where the agent chooses a pair of items at each round and observes…

Machine Learning · Computer Science 2022-06-14 Aadirupa Saha , Shubham Gupta

In this paper, we propose a novel model-free reinforcement learning algorithm to compute the optimal policies for a multi-agent system with $N$ cooperative agents where each agent privately observes it's own private type and publicly…

Systems and Control · Electrical Eng. & Systems 2020-03-24 Rajesh K Mishra , Deepanshu Vasal , Sriram Vishwanath

We study two-sided matching markets in which one side of the market (the players) does not have a priori knowledge about its preferences for the other side (the arms) and is required to learn its preferences from experience. Also, we assume…

Machine Learning · Computer Science 2021-06-23 Lydia T. Liu , Feng Ruan , Horia Mania , Michael I. Jordan

We extend trust region policy optimization (TRPO) to multi-agent reinforcement learning (MARL) problems. We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. By…

Artificial Intelligence · Computer Science 2023-08-08 Hepeng Li , Haibo He

To expand the applicability of decentralized online learning, previous studies have proposed several algorithms for decentralized online continuous submodular maximization (D-OCSM) -- a non-convex/non-concave setting with continuous…

Machine Learning · Computer Science 2026-02-11 Yuanyu Wan , Yu Shen , Dingzhi Yu , Bo Xue , Mingli Song

Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or…

Machine Learning · Computer Science 2020-09-15 Huale Li , Xuan Wang , Fengwei Jia , Yifan Li , Yulin Wu , Jiajia Zhang , Shuhan Qi

We consider the problem of simultaneous learning in stochastic games with many players in the finite-horizon setting. While the typical target solution for a stochastic game is a Nash equilibrium, this is intractable with many players. We…

Computer Science and Game Theory · Computer Science 2022-10-27 William Brown

On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between…

Robotics · Computer Science 2019-07-10 Jonathan N. Lee , Michael Laskey , Ajay Kumar Tanwani , Anil Aswani , Ken Goldberg

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Computer Science 2014-08-12 Aristide Tossou , Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Statistics 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…

Machine Learning · Computer Science 2024-11-06 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou