English
Related papers

Related papers: Greedification Operators for Policy Optimization: …

200 papers

Policy gradient algorithms have been successfully applied to enhance the reasoning capabilities of large language models (LLMs). KL regularization is ubiquitous, yet the design surface, choice of KL direction (forward vs. reverse),…

Machine Learning · Computer Science 2026-02-20 Yifan Zhang , Yifeng Liu , Huizhuo Yuan , Yang Yuan , Quanquan Gu , Andrew Chi-Chih Yao

As machine learning algorithms increasingly influence critical decision making in different application areas, understanding human strategic behavior in response to these systems becomes vital. We explore individuals' choice between…

Machine Learning · Computer Science 2026-03-17 Sura Alhanouti , Parinaz Naghizadeh

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

Machine Learning · Computer Science 2023-11-13 Jared Markowitz , Edward W. Staley

The experience replay mechanism allows agents to use the experiences multiple times. In prior works, the sampling probability of the transitions was adjusted according to their importance. Reassigning sampling probabilities for every…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Furkan B. Mutlu , Suleyman S. Kozat

Sequence prediction models can be learned from example sequences with a variety of training algorithms. Maximum likelihood learning is simple and efficient, yet can suffer from compounding error at test time. Reinforcement learning such as…

Machine Learning · Computer Science 2019-07-02 Bowen Tan , Zhiting Hu , Zichao Yang , Ruslan Salakhutdinov , Eric Xing

Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms that strictly respect these theoretical frameworks have proven…

Machine Learning · Computer Science 2024-11-21 Jakub Grudzien Kuba , Christian Schroeder de Witt , Jakob Foerster

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using…

Artificial Intelligence · Computer Science 2015-12-15 Lucas Lehnert , Doina Precup

Proximal Policy Optimization (PPO) is a widely used reinforcement learning algorithm known for its stability and sample efficiency, but it often suffers from premature convergence due to limited exploration. In this paper, we propose POEM…

Neural and Evolutionary Computing · Computer Science 2026-01-22 Casimir Czworkowski , Stephen Hornish , Alhassan S. Yasin

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

We consider the problem of approximating a given element $f$ from a Hilbert space $\mathcal{H}$ by means of greedy algorithms and the application of such procedures to the regression problem in statistical learning theory. We improve on the…

Statistics Theory · Mathematics 2009-09-29 Andrew R. Barron , Albert Cohen , Wolfgang Dahmen , Ronald A. DeVore

We study the policy testing problem in discounted Markov decision processes (MDPs) in the fixed-confidence setting under a generative model with static sampling. The goal is to decide whether the value of a given policy exceeds a specified…

Machine Learning · Statistics 2026-04-21 Kaito Ariu , Po-An Wang , Alexandre Proutiere , Kenshi Abe

This letter studies the problem of minimizing increasing set functions, or equivalently, maximizing decreasing set functions, over the base of a matroid. This setting has received great interest, since it generalizes several applied…

Optimization and Control · Mathematics 2021-03-02 Orcun Karaca , Daniel Tihanyi , Maryam Kamgarpour

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering updates but often…

Machine Learning · Computer Science 2025-12-30 Wang Zixian

As large language models advance toward superhuman performance, ensuring their alignment with human values and abilities grows increasingly complex. Weak-to-strong generalization offers a promising approach by leveraging predictions from…

Machine Learning · Computer Science 2025-05-29 Wei Yao , Wenkai Yang , Ziqiao Wang , Yankai Lin , Yong Liu

The approximation of a discrete probability distribution $\mathbf{t}$ by an $M$-type distribution $\mathbf{p}$ is considered. The approximation error is measured by the informational divergence $\mathbb{D}(\mathbf{t}\Vert\mathbf{p})$, which…

Information Theory · Computer Science 2016-07-28 Bernhard C. Geiger , Georg Böcherer

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

The forward Kullback-Leibler (KL) divergence is a ubiquitous objective for fitting a parameterized distribution to samples due to its tractability and equivalence to maximum likelihood estimation (MLE). Its inherent asymmetry, however, may…

Machine Learning · Computer Science 2026-05-12 Omri Ben-Dov , Luiz F. O. Chamon

We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint…

Machine Learning · Computer Science 2011-09-22 Sarah Filippi , Olivier Cappé , Aurélien Garivier