English
Related papers

Related papers: Exploration Bonus for Regret Minimization in Undis…

200 papers

In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs). However, existing algorithms either suffer from sub-optimal regret guarantees or computational inefficiencies. In…

Machine Learning · Computer Science 2024-06-04 Victor Boone , Zihan Zhang

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However,…

Artificial Intelligence · Computer Science 2016-04-06 Kenji Kawaguchi

This paper presents a new model-free algorithm for episodic finite-horizon Markov Decision Processes (MDP), Adaptive Multi-step Bootstrap (AMB), which enjoys a stronger gap-dependent regret bound. The first innovation is to estimate the…

Machine Learning · Computer Science 2021-07-05 Haike Xu , Tengyu Ma , Simon S. Du

We study algorithms for average-cost reinforcement learning problems with value function approximation. Our starting point is the recently proposed POLITEX algorithm, a version of policy iteration where the policy produced in each iteration…

Machine Learning · Computer Science 2019-08-29 Yasin Abbasi-Yadkori , Nevena Lazic , Csaba Szepesvari , Gellert Weisz

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 regret minimization under privacy constraints in episodic inhomogeneous linear Markov Decision Processes (MDPs), motivated by the growing use of reinforcement learning (RL) in personalized decision-making systems that rely on…

Machine Learning · Computer Science 2025-04-29 Sharan Sahu

In this work, we consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of infinite-horizon discounted cost Markov Decision Process (MDP). While…

Machine Learning · Statistics 2020-01-14 Devavrat Shah , Qiaomin Xie , Zhi Xu

We present two Policy Gradient-based algorithms with general parametrization in the context of infinite-horizon average reward Markov Decision Process (MDP). The first one employs Implicit Gradient Transport for variance reduction, ensuring…

Machine Learning · Computer Science 2025-05-13 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total…

Machine Learning · Computer Science 2020-05-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

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

Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal…

Machine Learning · Computer Science 2025-11-17 Ziyi Zhang , Yorie Nakahira , Guannan Qu

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based…

Machine Learning · Computer Science 2020-06-25 Yi Tian , Jian Qian , Suvrit Sra

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While…

Machine Learning · Computer Science 2026-05-04 Haichen Hu , Jian Qian , David Simchi-Levi

We derive a novel asymptotic problem-dependent lower-bound for regret minimization in finite-horizon tabular Markov Decision Processes (MDPs). While, similar to prior work (e.g., for ergodic MDPs), the lower-bound is the solution to an…

Machine Learning · Computer Science 2021-06-25 Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the…

Machine Learning · Computer Science 2012-05-14 Peter L. Bartlett , Ambuj Tewari

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for…

Machine Learning · Computer Science 2024-12-13 Weitong Zhang , Zhiyuan Fan , Jiafan He , Quanquan Gu

In standard RL, a learner attempts to learn an optimal policy for a Markov Decision Process whose structure (e.g. state space) is known. In online model selection, a learner attempts to learn an optimal policy for an MDP knowing only that…

Machine Learning · Computer Science 2024-11-12 Alireza Masoumian , James R. Wright

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu