English
Related papers

Related papers: Near-Optimal Dynamic Regret for Adversarial Linear…

200 papers

We study the problem of determining an effective exploration strategy in static and non-linear optimization problems, which depend on an unknown scalar parameter to be learned from online collected noisy data. An optimal trade-off between…

Optimization and Control · Mathematics 2024-09-13 Ying Wang , Mirko Pasquini , Kévin Colin , Håkan Hjalmarsson

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and…

Machine Learning · Computer Science 2012-07-03 Gabor Bartok , Navid Zolghadr , Csaba Szepesvari

We study non-rectangular robust Markov decision processes under the average-reward criterion, where the ambiguity set couples transition probabilities across states and the adversary commits to a stationary kernel for the entire horizon. We…

Optimization and Control · Mathematics 2026-03-11 Shengbo Wang , Nian Si

We study variance-dependent regret bounds for Markov decision processes (MDPs). Algorithms with variance-dependent regret guarantees can automatically exploit environments with low variance (e.g., enjoying constant regret on deterministic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Zihan Zhang , Simon S. Du

We consider the problem of nonstochastic control with a sequence of quadratic losses, i.e., LQR control. We provide an efficient online algorithm that achieves an optimal dynamic (policy) regret of $\tilde{O}(\text{max}\{n^{1/3}…

Machine Learning · Computer Science 2022-06-22 Dheeraj Baby , Yu-Xiang Wang

We consider the problem of online control of systems with time-varying linear dynamics. This is a general formulation that is motivated by the use of local linearization in control of nonlinear dynamical systems. To state meaningful…

Machine Learning · Computer Science 2022-02-15 Paula Gradu , Elad Hazan , Edgar Minasyan

We study the stochastic shortest path problem with adversarial costs and known transition, and show that the minimax regret is $\widetilde{O}(\sqrt{DT^\star K})$ and $\widetilde{O}(\sqrt{DT^\star SA K})$ for the full-information setting and…

Machine Learning · Computer Science 2021-06-23 Liyu Chen , Haipeng Luo , Chen-Yu Wei

The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for…

Artificial Intelligence · Computer Science 2023-02-14 Marc Rigter , Bruno Lacerda , Nick Hawes

Performance of adaptive control policies is assessed through the regret with respect to the optimal regulator, which reflects the increase in the operating cost due to uncertainty about the dynamics parameters. However, available results in…

Systems and Control · Computer Science 2020-03-24 Mohamad Kazem Shirani Faradonbeh , Ambuj Tewari , George Michailidis

This paper investigates the problem of non-stationary linear bandits, where the unknown regression parameter is evolving over time. Existing studies develop various algorithms and show that they enjoy an…

Machine Learning · Computer Science 2021-12-23 Peng Zhao , Lijun Zhang , Yuan Jiang , Zhi-Hua Zhou

We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations…

Machine Learning · Computer Science 2013-03-19 Odalric-Ambrym Maillard , Phuong Nguyen , Ronald Ortner , Daniil Ryabko

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problems. In this paper, we introduce dynamic policy regret as the…

Machine Learning · Computer Science 2023-08-16 Peng Zhao , Yu-Hu Yan , Yu-Xiang Wang , Zhi-Hua Zhou

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

We propose a novel change point detection approach for online learning control with full information feedback (state, disturbance, and cost feedback) for unknown time-varying dynamical systems. We show that our algorithm can achieve a…

Systems and Control · Electrical Eng. & Systems 2023-03-28 Deepan Muthirayan , Ruijie Du , Yanning Shen , Pramod P. Khargonekar

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

Machine Learning · Computer Science 2021-03-01 Naman Agarwal , Elad Hazan , Anirudha Majumdar , Karan Singh

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We propose a new regret minimization algorithm for episodic sparse linear Markov decision process (SMDP) where the state-transition distribution is a linear function of observed features. The only previously known algorithm for SMDP…

Machine Learning · Statistics 2023-10-25 Wonyoung Kim , Garud Iyengar , Assaf Zeevi

The problem of reinforcement learning in an unknown and discrete Markov Decision Process (MDP) under the average-reward criterion is considered, when the learner interacts with the system in a single stream of observations, starting from an…

Machine Learning · Statistics 2018-03-06 Mohammad Sadegh Talebi , Odalric-Ambrym Maillard

We study a $K$-armed non-stationary bandit model where rewards change smoothly, as captured by H\"{o}lder class assumptions on rewards as functions of time. Such smooth changes are parametrized by a H\"{o}lder exponent $\beta$ and…

Machine Learning · Statistics 2025-02-27 Joe Suk