English
Related papers

Related papers: Fine-Grained Gap-Dependent Bounds for Tabular MDPs…

200 papers

We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP). This is motivated by the widespread applications of reinforcement learning (RL) in real-world…

Machine Learning · Computer Science 2021-12-21 Sayak Ray Chowdhury , Xingyu Zhou

We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire…

Machine Learning · Computer Science 2025-02-07 Tal Lancewicki , Yishay Mansour

Reinforcement learning (RL) with linear function approximation has received increasing attention recently. However, existing work has focused on obtaining $\sqrt{T}$-type regret bound, where $T$ is the number of interactions with the MDP.…

Machine Learning · Computer Science 2021-02-19 Jiafan He , Dongruo Zhou , Quanquan Gu

We study the reinforcement learning problem for discounted Markov Decision Processes (MDPs) under the tabular setting. We propose a model-based algorithm named UCBVI-$\gamma$, which is based on the \emph{optimism in the face of uncertainty…

Machine Learning · Computer Science 2022-01-04 Jiafan He , Dongruo Zhou , Quanquan Gu

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do…

Machine Learning · Computer Science 2022-08-23 Weichao Mao , Kaiqing Zhang , Ruihao Zhu , David Simchi-Levi , Tamer Başar

The contextual combinatorial semi-bandit problem with linear payoff functions is a decision-making problem in which a learner chooses a set of arms with the feature vectors in each round under given constraints so as to maximize the sum of…

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 reinforcement learning, Monte Carlo algorithms update the Q function by averaging the episodic returns. In the Monte Carlo UCB (MC-UCB) algorithm, the action taken in each state is the action that maximizes the Q function plus an Upper…

Machine Learning · Computer Science 2025-03-18 Zixuan Dong , Che Wang , Keith Ross

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

This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}. Specifically, we consider tabular MDP with $S$ states, $A$ actions, a…

Machine Learning · Computer Science 2022-06-17 Zihan Zhang , Xiangyang Ji , Simon S. Du

We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…

Machine Learning · Computer Science 2024-11-06 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov Decision Processes (CMDPs), in which an agent aims to maximize the expected cumulative reward subject to a cumulative constraint on the…

Machine Learning · Computer Science 2023-03-13 Honghao Wei , Arnob Ghosh , Ness Shroff , Lei Ying , Xingyu Zhou

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

We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown environment without observing external rewards. Reward-free exploration aims to enable…

Machine Learning · Computer Science 2026-05-18 Oran Ridel , Alon Cohen

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e. those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. $arm$). We study a particular case of the rested…

Machine Learning · Statistics 2024-11-28 Marco Fiandri , Alberto Maria Metelli , Francesco Trov`o

This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a…

Machine Learning · Computer Science 2024-10-15 Kihyun Yu , Duksang Lee , William Overman , Dabeen Lee

We address reinforcement learning problems with finite state and action spaces where the underlying MDP has some known structure that could be potentially exploited to minimize the exploration rates of suboptimal (state, action) pairs. For…

Machine Learning · Computer Science 2018-11-30 Jungseul Ok , Alexandre Proutiere , Damianos Tranos

Sequential decisions in volatile, high-stakes settings require more than maximizing expected return; they require principled uncertainty management. This paper presents the Uncertainty-Aware Markov Decision Process (UAMDP), a unified…

Machine Learning · Computer Science 2025-12-19 Michal Koren , Or Peretz , Tai Dinh , Philip S. Yu

We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between…

Machine Learning · Computer Science 2021-09-14 Nadav Merlis , Shie Mannor