English
Related papers

Related papers: On Lower Bounds for Regret in Reinforcement Learni…

200 papers

In this paper we provide provable regret guarantees for an online meta-learning receding horizon control algorithm in an iterative control setting. We consider the setting where, in each iteration the system to be controlled is a linear…

Systems and Control · Electrical Eng. & Systems 2022-11-02 Deepan Muthirayan , Pramod P. Khargonekar

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the…

Machine Learning · Computer Science 2023-10-27 Tiancheng Jin , Junyan Liu , Chloé Rouyer , William Chang , Chen-Yu Wei , Haipeng Luo

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforcement Learning (RL), on the other hand, can learn near-optimal…

Artificial Intelligence · Computer Science 2026-02-12 Finn Rietz , Mart Kartašev , Petter Ögren , Johannes A. Stork

Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for…

Machine Learning · Computer Science 2020-01-28 Liyuan Zheng , Lillian J. Ratliff

We study online reinforcement learning for finite-horizon deterministic control systems with {\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is…

Machine Learning · Computer Science 2019-05-07 Lin F. Yang , Chengzhuo Ni , Mengdi Wang

We study online learning problems in which the learner has extra knowledge about the adversary's behaviour, i.e., in game-theoretic settings where opponents typically follow some no-external regret learning algorithms. Under this…

Machine Learning · Computer Science 2023-02-15 Le Cong Dinh , Tri-Dung Nguyen , Alain Zemkoho , Long Tran-Thanh

Reinforcement learning algorithms are usually stated without theoretical guarantees regarding their performance. Recently, Jin, Yang, Wang, and Jordan (COLT 2020) showed a polynomial-time reinforcement learning algorithm (namely, LSVI-UCB)…

Machine Learning · Computer Science 2024-11-19 Philips George John , Arnab Bhattacharyya , Silviu Maniu , Dimitrios Myrisiotis , Zhenan Wu

Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\Omega(\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

We study the fundamental problem of prediction with expert advice and develop regret lower bounds for a large family of algorithms for this problem. We develop simple adversarial primitives, that lend themselves to various combinations…

Machine Learning · Computer Science 2016-07-15 Nick Gravin , Yuval Peres , Balasubramanian Sivan

To cope with changing environments, recent developments in online learning have introduced the concepts of adaptive regret and dynamic regret independently. In this paper, we illustrate an intrinsic connection between these two concepts by…

Machine Learning · Computer Science 2018-06-05 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

In online learning the performance of an algorithm is typically compared to the performance of a fixed function from some class, with a quantity called regret. Forster proposed a last-step min-max algorithm which was somewhat simpler than…

Machine Learning · Computer Science 2013-01-28 Edward Moroshko , Koby Crammer

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 analyze and evaluate an online gradient descent algorithm with adaptive per-coordinate adjustment of learning rates. Our algorithm can be thought of as an online version of batch gradient descent with a diagonal preconditioner. This…

Machine Learning · Computer Science 2010-02-26 Matthew Streeter , H. Brendan McMahan

Regret minimization is a powerful method for finding Nash equilibria in Normal-Form Games (NFGs) and Extensive-Form Games (EFGs), but it typically guarantees convergence only for the average strategy. However, computing the average strategy…

Computer Science and Game Theory · Computer Science 2025-09-18 Hang Ren , Yulin Wu , Shuhan Qi , Jiajia Zhang , Xiaozhen Sun , Tianzi Ma , Xuan Wang

We study online learning in contextual pay-per-click auctions where at each of the $T$ rounds, the learner receives some context along with a set of ads and needs to make an estimate on their click-through rate (CTR) in order to run a…

Machine Learning · Computer Science 2023-10-10 Mengxiao Zhang , Haipeng Luo

In this work, we study the learning theory of reward modeling with pairwise comparison data using deep neural networks. We establish a novel non-asymptotic regret bound for deep reward estimators in a non-parametric setting, which depends…

Machine Learning · Statistics 2025-05-13 Yuanhang Luo , Yeheng Ge , Ruijian Han , Guohao Shen

In the classic expert problem, $\Phi$-regret measures the gap between the learner's total loss and that achieved by applying the best action transformation $\phi \in \Phi$. A recent work by Lu et al., [2025] introduces an adaptive algorithm…

Machine Learning · Computer Science 2025-12-16 Soumita Hait , Ping Li , Haipeng Luo , Mengxiao Zhang

We consider the problem of recommending relevant labels (items) for a given data point (user). In particular, we are interested in the practically important setting where the evaluation is with respect to non-decomposable (over labels)…

Machine Learning · Computer Science 2016-06-08 Prateek Jain , Nagarajan Natarajan