English
Related papers

Related papers: Refined Policy Improvement Bounds for MDPs

200 papers

Finding optimal policies for Partially Observable Markov Decision Processes (POMDPs) is challenging due to their uncountable state spaces when transformed into fully observable Markov Decision Processes (MDPs) using belief states.…

Optimization and Control · Mathematics 2024-09-09 Yunus Emre Demirci , Ali Devran Kara , Serdar Yüksel

Novel advanced policy gradient (APG) algorithms, such as proximal policy optimization (PPO), trust region policy optimization, and their variations, have become the dominant reinforcement learning (RL) algorithms because of their ease of…

Optimization and Control · Mathematics 2022-05-05 Mark Gluzman

We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy…

Artificial Intelligence · Computer Science 2014-05-13 Bruno Scherrer

We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the…

Machine Learning · Computer Science 2026-05-14 Amer Essakine , Claire Vernade

Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited,…

Machine Learning · Computer Science 2021-02-12 Botao Hao , Nevena Lazic , Yasin Abbasi-Yadkori , Pooria Joulani , Csaba Szepesvari

Markov Decision Problems (MDPs) provide a foundational framework for modelling sequential decision-making across diverse domains, guided by optimality criteria such as discounted and average rewards. However, these criteria have inherent…

Artificial Intelligence · Computer Science 2025-08-26 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs has been limited, with most existing results restricted to…

Optimization and Control · Mathematics 2026-02-23 Jongmin Lee , Ernest K. Ryu

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer,…

Machine Learning · Computer Science 2020-07-07 Ron Amit , Ron Meir , Kamil Ciosek

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

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…

Machine Learning · Computer Science 2025-10-15 Nianyi Lin , Jiajie Zhang , Lei Hou , Juanzi Li

Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Xiaoyang Tan , Zhe Wu , Junliang Xing

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

Artificial Intelligence · Computer Science 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most…

Machine Learning · Computer Science 2026-02-11 Hanyong Wang , Menglong Yang

Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level…

In this work, we consider a cooperative multi-agent Markov decision process (MDP) involving m agents. At each decision epoch, all the m agents independently select actions in order to maximize a common long-term objective. In the policy…

Machine Learning · Computer Science 2024-05-01 Lakshmi Mandal , Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck:…

Machine Learning · Computer Science 2026-03-06 Yuan Li , Bo Wang , Yufei Gao , Yuqian Yao , Xinyuan Wang , Zhangyue Yin , Xipeng Qiu

Regularized MDPs serve as a smooth version of original MDPs. However, biased optimal policy always exists for regularized MDPs. Instead of making the coefficient{\lambda}of regularized term sufficiently small, we propose an adaptive…

Machine Learning · Computer Science 2020-11-03 Wenhao Yang , Xiang Li , Guangzeng Xie , Zhihua Zhang

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long…

Artificial Intelligence · Computer Science 2026-03-03 Gang Li , Yan Chen , Ming Lin , Tianbao Yang
‹ Prev 1 3 4 5 6 7 10 Next ›