English
Related papers

Related papers: A Reduction-based Framework for Sequential Decisio…

200 papers

In real-world multi-agent systems (MASs), observation delays are ubiquitous, preventing agents from making decisions based on the environment's true state. An individual agent's local observation typically comprises multiple components from…

Multiagent Systems · Computer Science 2025-11-13 Songchen Fu , Siang Chen , Shaojing Zhao , Letian Bai , Ta Li , Yonghong Yan

We study online learning in constrained Markov decision processes (CMDPs) with adversarial losses and stochastic hard constraints, under bandit feedback. We consider three scenarios. In the first one, we address general CMDPs, where we…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

Motivated from Bertsekas' recent study on policy iteration (PI) for solving the problems of infinite-horizon discounted Markov decision processes (MDPs) in an on-line setting, we develop an off-line PI integrated with a multi-policy…

Optimization and Control · Mathematics 2021-12-07 Hyeong Soo Chang

The multi-armed bandits (MAB) framework is a widely used approach for sequential decision-making, where a decision-maker selects an arm in each round with the goal of maximizing long-term rewards. In many practical applications, such as…

Machine Learning · Statistics 2026-05-21 Sakshi Arya , Hyebin Song

We develop a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for both first-order and bandit convex optimization. Our approach introduces a continuous-time model under…

Machine Learning · Computer Science 2026-02-04 Alexander Ryabchenko , Idan Attias , Daniel M. Roy

We investigate online Markov Decision Processes (MDPs) with adversarially changing loss functions and known transitions. We choose dynamic regret as the performance measure, defined as the performance difference between the learner and any…

Machine Learning · Computer Science 2022-08-29 Peng Zhao , Long-Fei Li , Zhi-Hua Zhou

This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping…

Machine Learning · Computer Science 2024-03-05 Mingyu Chen , Xuezhou Zhang

The feedback that AI systems (e.g., recommender systems, chatbots) collect from user interactions is a crucial source of training data. While short-term feedback (e.g., clicks, engagement) is widely used for training, there is ample…

Machine Learning · Computer Science 2025-05-29 Richa Rastogi , Yuta Saito , Thorsten Joachims

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

Achieving safety in autonomous multi-agent systems, particularly in time-critical tasks like rendezvous, is a critical challenge. In this paper, we propose a distributionally robust risk framework for analyzing cascading failures in…

Systems and Control · Electrical Eng. & Systems 2025-08-01 Vivek Pandey , Nader Motee

Multi-agent Markov Decision Processes (MMDPs) arise in a variety of applications including target tracking, control of multi-robot swarms, and multiplayer games. A key challenge in MMDPs occurs when the state and action spaces grow…

Multiagent Systems · Computer Science 2021-03-31 Dinuka Sahabandu , Luyao Niu , Andrew Clark , Radha Poovendran

Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly…

Machine Learning · Computer Science 2026-05-07 Ziyuan Huang , Lina Alkarmi , Mingyan Liu

In this paper we are introducing a new reinforcement learning method for control problems in environments with delayed feedback. Specifically, our method employs stochastic planning, versus previous methods that used deterministic planning.…

Machine Learning · Computer Science 2024-02-02 Zhiyuan Yao , Ionut Florescu , Chihoon Lee

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

Machine Learning · Computer Science 2023-11-01 Reda Alami , Mohammed Mahfoud , Mastane Achab

In this paper, we study kernelized bandits with distributed biased feedback. This problem is motivated by several real-world applications (such as dynamic pricing, cellular network configuration, and policy making), where users from a large…

Machine Learning · Computer Science 2023-02-08 Fengjiao Li , Xingyu Zhou , Bo Ji

The standard formulation of Markov decision processes (MDPs) assumes that the agent's decisions are executed immediately. However, in numerous realistic applications such as robotics or healthcare, actions are performed with a delay whose…

Artificial Intelligence · Computer Science 2024-04-09 David Valensi , Esther Derman , Shie Mannor , Gal Dalal

In many real-world sequential decision-making problems, an action does not immediately reflect on the feedback and spreads its effects over a long time frame. For instance, in online advertising, investing in a platform produces an…

Machine Learning · Computer Science 2023-05-31 Marco Mussi , Alberto Maria Metelli , Marcello Restelli

We propose and investigate a class of new algorithms for sequential decision making that interacts with \textit{a batch of users} simultaneously instead of \textit{a user} at each decision epoch. This type of batch models is motivated by…

Machine Learning · Statistics 2020-03-02 Chi-Hua Wang , Guang Cheng

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output…

Artificial Intelligence · Computer Science 2026-05-12 Wenzhi Fang , Liangqi Yuan , Guangchen Lan , Dong-Jun Han , Christopher G. Brinton

Caching is crucial for system performance, but the delayed hit phenomenon, where requests queue during lengthy fetches after a cache miss, significantly degrades user-perceived latency in modern high-throughput systems. While prior works…

Networking and Internet Architecture · Computer Science 2025-05-22 Bowen Jiang , Chaofan Ma