English
Related papers

Related papers: Near-Optimal Regret for Policy Optimization in Con…

200 papers

We consider discounted infinite-horizon constrained Markov decision processes (CMDPs), where the goal is to find an optimal policy that maximizes the expected cumulative reward while satisfying expected cumulative constraints. Motivated by…

Machine Learning · Computer Science 2025-03-04 Tingting Ni , Maryam Kamgarpour

We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\mathcal{O}(\sqrt{T})$ for learning over $T$ rounds, when the total…

Machine Learning · Computer Science 2020-10-16 Chen-Yu Wei , Haipeng Luo , Alekh Agarwal

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…

Machine Learning · Computer Science 2022-02-14 Tengyang Xie , Nan Jiang , Huan Wang , Caiming Xiong , Yu Bai

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Machine Learning · Computer Science 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman

We propose and study an online version of min-max optimization based on cumulative saddle points under a variety of performance measures beyond convex-concave settings. After first observing the incompatibility of (static) Nash equilibrium…

Machine Learning · Computer Science 2026-02-12 Abhijeet Vyas , Brian Bullins

We study high-probability regret bounds for adversarial $K$-armed bandits with time-varying feedback graphs over $T$ rounds. For general strongly observable graphs, we develop an algorithm that achieves the optimal regret…

Machine Learning · Computer Science 2023-01-31 Haipeng Luo , Hanghang Tong , Mengxiao Zhang , Yuheng Zhang

We study an approximation method for partially observed Markov decision processes (POMDPs) with continuous spaces. Belief MDP reduction, which has been the standard approach to study POMDPs requires rigorous approximation methods for…

Optimization and Control · Mathematics 2025-01-20 Ali Devran Kara , Erhan Bayraktar , Serdar Yuksel

We present the first gap-dependent analysis of regret and communication cost for on-policy federated $Q$-Learning in tabular episodic finite-horizon Markov decision processes (MDPs). Existing FRL methods focus on worst-case scenarios,…

Machine Learning · Statistics 2025-09-19 Haochen Zhang , Zhong Zheng , Lingzhou Xue

In this paper, we broaden the horizon of online convex optimization (OCO), and consider multi-objective OCO, where there are $K$ distinct loss function sequences, and an algorithm has to choose its action at time $t$, before the $K$ loss…

Machine Learning · Computer Science 2026-02-11 Rahul Vaze , Sumiran Mishra

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially…

Machine Learning · Computer Science 2023-10-04 Xuefeng Gao , Xun Yu Zhou

We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature…

Machine Learning · Computer Science 2026-05-18 Rahul Singh , Siddharth Chandak , Eric Moulines , Vivek S. Borkar , Nicholas Bambos

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

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

A well-studied generalization of the standard online convex optimization (OCO) framework is constrained online convex optimization (COCO). In COCO, on every round, a convex cost function and a convex constraint function are revealed to the…

Machine Learning · Computer Science 2024-10-29 Abhishek Sinha , Rahul Vaze

In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a stochastic gradient of its own objective function in the previous time, and can communicate with its neighbors via a…

Optimization and Control · Mathematics 2024-01-29 Yuchen Yang , Kaihong Lu , Long Wang

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit…

Machine Learning · Computer Science 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property.…

Optimization and Control · Mathematics 2019-07-02 Omid Sadeghi , Maryam Fazel

We consider a stochastic inventory control problem under censored demands, lost sales, and positive lead times. This is a fundamental problem in inventory management, with significant literature establishing near-optimality of a simple…

Machine Learning · Computer Science 2019-05-14 Shipra Agrawal , Randy Jia