English
Related papers

Related papers: Byzantine-Resilient Decentralized TD Learning with…

200 papers

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…

Optimization and Control · Mathematics 2020-04-29 Donghwan Lee , Jianghai Hu

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and complex mapping space,…

Detection and mitigation of Byzantine behaviors in a decentralized learning setting is a daunting task, especially when the data distribution at the users is heterogeneous. As our main contribution, we propose Basil, a fast and…

Systems and Control · Electrical Eng. & Systems 2022-10-07 Ahmed Roushdy Elkordy , Saurav Prakash , A. Salman Avestimehr

This report considers the problem of resilient distributed optimization and stochastic learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has its own local cost function. The agents…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-15 Shuo Liu , Nirupam Gupta , Nitin H. Vaidya

In this paper, we propose a first-order distributed optimization algorithm that is provably robust to Byzantine failures-arbitrary and potentially adversarial behavior, where all the participating agents are prone to failure. We model each…

Optimization and Control · Mathematics 2022-07-27 Berkay Turan , Cesar A. Uribe , Hoi-To Wai , Mahnoosh Alizadeh

This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to…

Robotics · Computer Science 2025-04-23 Jun Wang , Hosein Hasanbeig , Kaiyuan Tan , Zihe Sun , Yiannis Kantaros

Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms.…

Machine Learning · Computer Science 2025-06-19 Bing Liu , Chengcheng Zhao , Li Chai , Peng Cheng , Yaonan Wang

In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic conditions the policies of the cooperative agents based on a…

Artificial Intelligence · Computer Science 2023-04-04 Siddarth Singh , Benjamin Rosman

We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved…

Machine Learning · Computer Science 2017-12-29 Huizhen Yu

This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation…

Machine Learning · Statistics 2024-05-03 Gen Li , Weichen Wu , Yuejie Chi , Cong Ma , Alessandro Rinaldo , Yuting Wei

This paper studies distributed online learning under Byzantine attacks. The performance of an online learning algorithm is often characterized by (adversarial) regret, which evaluates the quality of one-step-ahead decision-making when an…

Machine Learning · Computer Science 2023-12-06 Xingrong Dong , Zhaoxian Wu , Qing Ling , Zhi Tian

We consider the federated learning problem where data on workers are not independent and identically distributed (i.i.d.). During the learning process, an unknown number of Byzantine workers may send malicious messages to the central node,…

Machine Learning · Computer Science 2021-08-31 Jie Peng , Zhaoxian Wu , Qing Ling , Tianyi Chen

Designing efficient algorithms for multi-agent reinforcement learning (MARL) is fundamentally challenging because the size of the joint state and action spaces grows exponentially in the number of agents. These difficulties are exacerbated…

Machine Learning · Computer Science 2025-10-27 Emile Anand , Ishani Karmarkar , Guannan Qu

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

Machine Learning · Statistics 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are…

Machine Learning · Computer Science 2021-08-24 Nishanth Anand , Doina Precup

This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(lambda), LSTD(lambda), iLSTD, residual-gradient TD. It is asserted…

Machine Learning · Computer Science 2007-05-23 Manuel Loth , Philippe Preux

A unique challenge in Multi-Agent Reinforcement Learning (MARL) is the curse of multiagency, where the description length of the game as well as the complexity of many existing learning algorithms scale exponentially with the number of…

Machine Learning · Computer Science 2023-03-03 Yuanhao Wang , Qinghua Liu , Yu Bai , Chi Jin

Large language models are increasingly deployed as cooperating agents, yet their behavior in adversarial consensus settings has not been systematically studied. We evaluate LLM-based agents on a Byzantine consensus game over scalar values…

Multiagent Systems · Computer Science 2026-03-13 Frédéric Berdoz , Leonardo Rugli , Roger Wattenhofer

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

We propose a unified framework to study policy evaluation (PE) and the associated temporal difference (TD) methods for reinforcement learning in continuous time and space. We show that PE is equivalent to maintaining the martingale…

Machine Learning · Computer Science 2022-02-02 Yanwei Jia , Xun Yu Zhou