English
Related papers

Related papers: Corruption-robust Offline Multi-agent Reinforcemen…

200 papers

We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL). We propose a unified algorithm framework for randomized exploration in parallel Markov Decision Processes…

Machine Learning · Computer Science 2025-03-04 Hao-Lun Hsu , Weixin Wang , Miroslav Pajic , Pan Xu

We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes (MDP). For tabular MDP with $S$ states and $A$ actions, or linear MDP with anchor points and feature dimension $d$, given the collected $K$…

Machine Learning · Statistics 2022-02-11 Tongzheng Ren , Jialian Li , Bo Dai , Simon S. Du , Sujay Sanghavi

Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are available across medical institutions, they…

Machine Learning · Statistics 2024-01-30 Doudou Zhou , Yufeng Zhang , Aaron Sonabend-W , Zhaoran Wang , Junwei Lu , Tianxi Cai

While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety critical applications…

Multiagent Systems · Computer Science 2022-04-19 Jun Guo , Yonghong Chen , Yihang Hao , Zixin Yin , Yin Yu , Simin Li

In linear bandits, how can a learner effectively learn when facing corrupted rewards? While significant work has explored this question, a holistic understanding across different adversarial models and corruption measures is lacking, as is…

Machine Learning · Computer Science 2024-10-21 Haolin Liu , Artin Tajdini , Andrew Wagenmaker , Chen-Yu Wei

This paper develops a formal framework to assess policies of learning algorithms in economic games. We investigate whether reinforcement-learning agents with collusive pricing policies can successfully extrapolate collusive behavior from…

General Economics · Economics 2022-01-06 Nicolas Eschenbaum , Filip Mellgren , Philipp Zahn

We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers. Classical approaches such as Behavior Cloning assumes that demonstrations are collected by an…

Machine Learning · Computer Science 2022-02-01 Liu Liu , Ziyang Tang , Lanqing Li , Dijun Luo

We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a Reproducing Kernel Hilbert Space (RKHS). The key challenge is…

Machine Learning · Computer Science 2022-08-11 Chris Junchi Li , Dongruo Zhou , Quanquan Gu , Michael I. Jordan

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…

Machine Learning · Computer Science 2018-03-28 Thodoris Lykouris , Vahab Mirrokni , Renato Paes Leme

Here we revisit the classic problem of linear quadratic estimation, i.e. estimating the trajectory of a linear dynamical system from noisy measurements. The celebrated Kalman filter gives an optimal estimator when the measurement noise is…

Machine Learning · Statistics 2021-11-12 Sitan Chen , Frederic Koehler , Ankur Moitra , Morris Yau

Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show that deep neural networks also exhibit vulnerability to…

Machine Learning · Computer Science 2022-04-15 Zhiyuan Zhang , Ruixuan Luo , Xuancheng Ren , Qi Su , Liangyou Li , Xu Sun

We study the problem of stochastic bandits with adversarial corruptions in the cooperative multi-agent setting, where $V$ agents interact with a common $K$-armed bandit problem, and each pair of agents can communicate with each other to…

Machine Learning · Computer Science 2021-06-09 Junyan Liu , Shuai Li , Dapeng Li

Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance. To alleviate this problem, we present an efficient robust algorithm…

Machine Learning · Computer Science 2021-02-16 Boyang Liu , Mengying Sun , Ding Wang , Pang-Ning Tan , Jiayu Zhou

We present an approach to reduce the communication required between agents in a Multi-Agent learning system by exploiting the inherent robustness of the underlying Markov Decision Process. We compute so-called robustness surrogate functions…

Multiagent Systems · Computer Science 2022-09-08 Daniel Jarne Ornia , Manuel Mazo

We study the problem of learning in zero-sum matrix games with repeated play and bandit feedback. Specifically, we focus on developing uncoupled algorithms that guarantee, without communication between players, the convergence of the…

Machine Learning · Computer Science 2026-04-20 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Michal Valko , Vianney Perchet

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback…

Machine Learning · Computer Science 2024-03-14 Runzhe Wu , Wen Sun

The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF),…

Artificial Intelligence · Computer Science 2026-04-14 Kun Liu , Liqun Chen

We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from…

Machine Learning · Computer Science 2024-05-07 Yingjie Fei , Ruitu Xu

This paper provides the first expert sample complexity characterization for learning a Nash equilibrium from expert data in Markov Games. We show that a new quantity named the single policy deviation concentrability coefficient is…

Machine Learning · Computer Science 2025-10-10 Till Freihaut , Luca Viano , Volkan Cevher , Matthieu Geist , Giorgia Ramponi

We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash…

Computer Science and Game Theory · Computer Science 2022-08-11 Benoit Duvocelle , Panayotis Mertikopoulos , Mathias Staudigl , Dries Vermeulen