English
Related papers

Related papers: Performance Bounds for Policy-Based Average Reward…

200 papers

We study cooperative multi-agent reinforcement learning in the setting of reward-free exploration, where multiple agents jointly explore an unknown MDP in order to learn its dynamics (without observing rewards). We focus on a tabular…

Machine Learning · Computer Science 2026-05-14 Idan Barnea , Orin Levy , Yishay Mansour

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards. The latter are…

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

Machine Learning · Computer Science 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

We study non-rectangular robust Markov decision processes under the average-reward criterion, where the ambiguity set couples transition probabilities across states and the adversary commits to a stationary kernel for the entire horizon. We…

Optimization and Control · Mathematics 2026-03-11 Shengbo Wang , Nian Si

We study reinforcement learning with linear function approximation and finite-memory approximations for partially observed Markov decision processes (POMDPs). We first present an algorithm for the value evaluation of finite-memory feedback…

Optimization and Control · Mathematics 2025-05-22 Ali Devran Kara

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 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy

We consider the problem of learning in adversarial Markov decision processes [MDPs] with an oblivious adversary in a full-information setting. The agent interacts with an environment during $T$ episodes, each of which consists of $H$…

Machine Learning · Computer Science 2025-03-06 Daniil Tiapkin , Evgenii Chzhen , Gilles Stoltz

The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work…

Artificial Intelligence · Computer Science 2012-05-14 Kevin Regan , Craig Boutilier

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which…

Machine Learning · Computer Science 2024-09-18 S. R. Eshwar , Mayank Motwani , Nibedita Roy , Gugan Thoppe

We present an optimistic Q-learning algorithm for regret minimization in average reward reinforcement learning under an additional assumption on the underlying MDP that for all policies, the time to visit some frequent state $s_0$ is finite…

Machine Learning · Computer Science 2025-06-17 Priyank Agrawal , Shipra Agrawal

We consider reinforcement learning (RL) methods for finding optimal policies in linear quadratic (LQ) mean field control (MFC) problems over an infinite horizon in continuous time, with common noise and entropy regularization. We study…

Optimization and Control · Mathematics 2024-08-06 Noufel Frikha , Huyên Pham , Xuanye Song

In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under…

Machine Learning · Computer Science 2023-03-21 Yuan Cheng , Ruiquan Huang , Jing Yang , Yingbin Liang

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin

We propose novel classical and quantum online algorithms for learning finite-horizon and infinite-horizon average-reward Markov Decision Processes (MDPs). Our algorithms are based on a hybrid exploration-generative reinforcement learning…

Machine Learning · Computer Science 2025-08-12 Andris Ambainis , Joao F. Doriguello , Debbie Lim

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory…

Machine Learning · Computer Science 2023-01-31 Uri Sherman , Tomer Koren , Yishay Mansour

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

In this paper we present an algorithm to compute risk averse policies in Markov Decision Processes (MDP) when the total cost criterion is used together with the average value at risk (AVaR) metric. Risk averse policies are needed when large…

Optimization and Control · Mathematics 2016-02-17 Stefano Carpin , Yin-Lam Chow , Marco Pavone