English
Related papers

Related papers: Provably Efficient Exploration in Constrained Rein…

200 papers

In this work, we study algorithms for learning in infinite-horizon undiscounted Markov decision processes (MDPs) with function approximation. We first show that the regret analysis of the Politex algorithm (a version of regularized policy…

Machine Learning · Computer Science 2021-02-26 Nevena Lazic , Dong Yin , Yasin Abbasi-Yadkori , Csaba Szepesvari

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs). We propose two near-optimal and oracle-efficient algorithms for FMDPs. Assuming oracle access to an FMDP planner, they enjoy a Bayesian and a…

Machine Learning · Statistics 2020-06-09 Ziping Xu , Ambuj Tewari

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $\pi' \leq \pi$ if data collected under…

Machine Learning · Statistics 2025-08-07 Zhongjun Zhang , Shipra Agrawal , Ilan Lobel , Sean R. Sinclair , Christina Lee Yu

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The multi-batch reinforcement learning framework, where the agent…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Yuhang Jiang , Yuan Zhou , Xiangyang Ji

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 analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm. Posterior sampling is an effective heuristic for decision-making under uncertainty that has been used to develop…

Machine Learning · Statistics 2026-03-10 Hamish Flynn , Joe Watson , Ingmar Posner , Jan Peters

This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based…

Machine Learning · Computer Science 2025-03-11 Max Buckley , Konstantinos Papathanasiou , Andreas Spanopoulos

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

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret…

Machine Learning · Computer Science 2023-12-13 Xiang Ji , Gen Li

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it…

Machine Learning · Computer Science 2020-06-09 Zihan Zhang , Yuan Zhou , Xiangyang Ji

We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a…

Machine Learning · Computer Science 2023-03-16 Rahul Singh , Abhishek Gupta , Ness B. Shroff

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$,…

Machine Learning · Computer Science 2024-05-03 Bingshan Hu , Zhiming Huang , Tianyue H. Zhang , Mathias Lécuyer , Nidhi Hegde

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \sqrt{\tau (\ln|S|+\ln|A|)T}\ln(T))$, where $S$…

Machine Learning · Computer Science 2019-05-28 Adrian Rivera Cardoso , He Wang , Huan Xu

We consider the problem of online reinforcement learning for the Stochastic Shortest Path (SSP) problem modeled as an unknown MDP with an absorbing state. We propose PSRL-SSP, a simple posterior sampling-based reinforcement learning…

Machine Learning · Computer Science 2021-06-11 Mehdi Jafarnia-Jahromi , Liyu Chen , Rahul Jain , Haipeng Luo

Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…

Machine Learning · Computer Science 2019-07-22 Vanessa Kosoy

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 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 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