English
Related papers

Related papers: The regret lower bound for communicating Markov De…

200 papers

The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and…

Machine Learning · Computer Science 2015-10-16 Yao Ma , Hao Zhang , Masashi Sugiyama

In the optimization of dynamical systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (CMDP). This paper considers a model-free approach to the problem, where the…

Machine Learning · Computer Science 2021-02-02 Qinbo Bai , Vaneet Aggarwal , Ather Gattami

A standard assumption in Reinforcement Learning is that the agent observes every visited state-action pair in the associated Markov Decision Process (MDP), along with the per-step rewards. Strong theoretical results are known in this…

Machine Learning · Computer Science 2026-02-03 Zhengjia Zhuo , Anupam Gupta , Viswanath Nagarajan

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 introduce and analyse two algorithms for exploration-exploitation in discrete and continuous Markov Decision Processes (MDPs) based on exploration bonuses. SCAL$^+$ is a variant of SCAL (Fruit et al., 2018) that performs efficient…

Machine Learning · Computer Science 2018-12-12 Jian Qian , Ronan Fruit , Matteo Pirotta , Alessandro Lazaric

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

While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically…

Machine Learning · Computer Science 2019-03-21 Ronan Fruit , Matteo Pirotta , Alessandro Lazaric

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Our contributions are twofold. First, we establish strong duality for weakly communicating average-reward…

Machine Learning · Computer Science 2026-05-13 Kihyun Yu , Beomhan Baek , Dabeen Lee

We consider the task of opportunistic channel access in a primary system composed of independent Gilbert-Elliot channels where the secondary (or opportunistic) user does not dispose of a priori information regarding the statistical…

Machine Learning · Statistics 2009-08-04 Sarah Filippi , Olivier Cappé , Aurélien Garivier

Markov decision processes (MDPs) are widely used in modeling decision making problems in stochastic environments. However, precise specification of the reward functions in MDPs is often very difficult. Recent approaches have focused on…

Artificial Intelligence · Computer Science 2012-02-20 Eunsoo Oh , Kee-Eung Kim

In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill

Multi-armed Bandit motivates methods with provable upper bounds on regret and also the counterpart lower bounds have been extensively studied in this context. Recently, Multi-agent Multi-armed Bandit has gained significant traction in…

Machine Learning · Computer Science 2023-08-17 Mengfan Xu , Diego Klabjan

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

This paper initiates the study of data-dependent regret bounds in constrained MAB settings. These bounds depend on the sequence of losses that characterize the problem instance. Thus, they can be much smaller than classical…

Machine Learning · Computer Science 2025-06-24 Gianmarco Genalti , Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but…

Machine Learning · Computer Science 2021-02-10 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the…

Machine Learning · Computer Science 2021-10-19 Shuang Qiu , Xiaohan Wei , Zhuoran Yang , Jieping Ye , Zhaoran Wang

We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on…

Machine Learning · Computer Science 2021-11-02 Rahul Madhavan , Aurghya Maiti , Gaurav Sinha , Siddharth Barman

Despite rapid progress in theoretical reinforcement learning (RL) over the last few years, most of the known guarantees are worst-case in nature, failing to take advantage of structure that may be known a priori about a given RL problem at…

Machine Learning · Computer Science 2021-10-26 Noah Golowich , Ankur Moitra

We consider multiple parallel Markov decision processes (MDPs) coupled by global constraints, where the time varying objective and constraint functions can only be observed after the decision is made. Special attention is given to how well…

Optimization and Control · Mathematics 2017-09-12 Xiaohan Wei , Hao Yu , Michael J. Neely

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill