English
Related papers

Related papers: Linear Convergence of Entropy-Regularized Natural …

200 papers

Reinforcement learning (RL) has gained attention for aligning large language models (LLMs) via reinforcement learning from human feedback (RLHF). The actor-only variants of Proximal Policy Optimization (PPO) are widely applied for their…

Optimization and Control · Mathematics 2025-12-19 Yin Liu , Qiming Dai , Junyu Zhang , Zaiwen Wen

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

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

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

This article examines large time behaviour of finite state mean-field interacting particle systems. Our first main result is a sharp estimate (in the exponential scale) on the time required for convergence of the empirical measure process…

Probability · Mathematics 2021-03-02 Sarath Yasodharan , Rajesh Sundaresan

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\epsilon$-approximate…

Machine Learning · Computer Science 2019-05-30 Pan Xu , Felicia Gao , Quanquan Gu

While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to…

Optimization and Control · Mathematics 2023-04-25 Feiran Zhao , Xingyun Fu , Keyou You

Flow $Q$-learning has recently been introduced to integrate learning from expert demonstrations into an actor-critic structure. Central to this innovation is the ``the one-step policy'' network, which is optimized through a $Q$-function…

Systems and Control · Electrical Eng. & Systems 2025-11-17 Farnaz Adib Yaghmaie , Arunava Naha

Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Zafarali Ahmed , Doina Precup

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts with the environment by generating noisy controls…

Machine Learning · Computer Science 2023-09-18 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

Entropy regularization is known to improve exploration in sequential decision-making problems. We show that this same mechanism can also lead to nearly unbiased and lower-variance estimates of the mean reward in the optimize-and-estimate…

Machine Learning · Computer Science 2022-08-26 Ben Chugg , Peter Henderson , Jacob Goldin , Daniel E. Ho

With the rapid discovery of emergent phenomena in deep learning and large language models, understanding their cause has become an urgent need. Here, we propose a rigorous entropic-force theory for understanding the learning dynamics of…

Machine Learning · Computer Science 2026-02-04 Liu Ziyin , Yizhou Xu , Isaac Chuang

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems,…

Optimization and Control · Mathematics 2024-05-07 Sara Klein , Simon Weissmann , Leif Döring

Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with…

Machine Learning · Computer Science 2026-05-19 Yevhen Shcherbinin , Arina Redina , Maxim Kalpin , Vlad Kochetov

Matrix completion has attracted much interest in the past decade in machine learning and computer vision. For low-rank promotion in matrix completion, the nuclear norm penalty is convenient due to its convexity but has a bias problem.…

Machine Learning · Computer Science 2019-03-05 Fei Wen , Rendong Ying , Peilin Liu , Trieu-Kien Truong

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Machine Learning · Computer Science 2024-05-21 G. Welper

The convergence of deterministic policy gradient under the Hadamard parameterization is studied in the tabular setting and the linear convergence of the algorithm is established. To this end, we first show that the error decreases at an…

Optimization and Control · Mathematics 2023-11-28 Jiacai Liu , Jinchi Chen , Ke Wei

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how…

Machine Learning · Computer Science 2024-12-11 Tian Tian , Lin F. Yang , Csaba Szepesvári