English
Related papers

Related papers: KL-Entropy-Regularized RL with a Generative Model …

200 papers

Reinforcement learning (RL) for exponential-utility optimization in discounted Markov decision processes (MDPs) lacks principled value-based algorithms. We address this gap in the fixed risk-aversion setting. Building on the Bellman-type…

Machine Learning · Computer Science 2026-05-11 Gugan Thoppe , L. A. Prashanth , Ankur Naskar , Sanjay Bhat

Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance. Yet, only little is understood theoretically about why KL regularization helps, so far.…

Machine Learning · Computer Science 2021-01-07 Nino Vieillard , Tadashi Kozuno , Bruno Scherrer , Olivier Pietquin , Rémi Munos , Matthieu Geist

Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical reasoning and code generation tasks. Despite extensive exploration of reward processing strategies and…

Machine Learning · Computer Science 2026-02-05 Rui Yuan , Mykola Khandoga , Vinay Kumar Sankarapu

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

Machine Learning · Computer Science 2024-01-01 Laixi Shi , Yuejie Chi

This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator). We first consider $\gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space…

Machine Learning · Computer Science 2025-03-18 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

We study the problem of deployment efficient reinforcement learning (RL) with linear function approximation under the \emph{reward-free} exploration setting. This is a well-motivated problem because deploying new policies is costly in…

Machine Learning · Computer Science 2023-02-23 Dan Qiao , Yu-Xiang Wang

We consider the parameter estimation problem of a probabilistic generative model prescribed using a natural exponential family of distributions. For this problem, the typical maximum likelihood estimator usually overfits under limited…

Machine Learning · Statistics 2020-10-13 Viet Anh Nguyen , Xuhui Zhang , Jose Blanchet , Angelos Georghiou

We study the sample complexity of obtaining an $\epsilon$-optimal policy in \emph{Robust} discounted Markov Decision Processes (RMDPs), given only access to a generative model of the nominal kernel. This problem is widely studied in the…

Machine Learning · Computer Science 2024-06-07 Pierre Clavier , Erwan Le Pennec , Matthieu Geist

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Machine Learning · Computer Science 2026-04-23 Jingyi Wang , Lei Zhu , Tengjin Weng , Song-Li Wu , Haochen Tan , Jierun Chen , Chaofan Tao , Haoli Bai , Lu Hou , Lifeng Shang , Xiao-Ping Zhang

Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the…

Machine Learning · Computer Science 2022-03-01 Frederik Kunstner , Raunak Kumar , Mark Schmidt

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from…

Machine Learning · Computer Science 2026-05-22 Shourov Joarder , Diganta Sikdar , Ahsan Habib Akash , Binod Bhattarai , Prashnna Gyawali

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

In this paper, we focus on the problem of inferring the underlying reward function of an expert given demonstrations, which is often referred to as inverse reinforcement learning (IRL). In particular, we propose a model-free density-based…

Robotics · Computer Science 2016-10-03 Sungjoon Choi , Kyungjae Lee , Andy Park , Songhwai Oh

We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as…

Machine Learning · Computer Science 2021-02-04 Ming Yin , Yu Bai , Yu-Xiang Wang

Reinforcement learning with verifiable rewards (RLVR) has recently enhanced the reasoning capabilities of large language models (LLMs), particularly for mathematical problem solving. However, a fundamental limitation remains: as the…

Machine Learning · Computer Science 2025-11-03 Wenhao Deng , Long Wei , Chenglei Yu , Tailin Wu

Policy mirror descent (PMD) provides a principled framework for reinforcement learning (RL) by iteratively solving KL-regularized policy improvement subproblems. While this approach has been adopted in training advanced LLMs such as Kimi…

Machine Learning · Computer Science 2026-02-06 Zhenghao Xu , Qin Lu , Changlong Yu , Tuo Zhao

Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a given class, deviate from desired values. We frame calibration as a constrained optimization…

Machine Learning · Statistics 2026-05-29 Henry D. Smith , Nathaniel L. Diamant , Brian L. Trippe

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top-$K$ activation retrieval or optimization with regularization). In this…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Guancheng Zhou , Yisi Luo , Zhengfu He , Zhenyu Jin , Xuyang Ge , Wentao Shu , Deyu Meng , Xipeng Qiu

Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its…

Machine Learning · Computer Science 2025-03-05 Jiajun He , Wenlin Chen , Mingtian Zhang , David Barber , José Miguel Hernández-Lobato