English
Related papers

Related papers: On Convergence Rate of Adaptive Multiscale Value F…

200 papers

In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for…

Machine Learning · Computer Science 2025-01-20 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

Regularization plays a key role in a variety of optimization formulations of inverse problems. A recurring theme in regularization approaches is the selection of regularization parameters, and their effect on the solution and on the optimal…

Optimization and Control · Mathematics 2018-08-23 Aleksandr Y. Aravkin , James V. Burke , Michael P. Friedlander

Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studies have established regret guarantees under worst-case…

Machine Learning · Statistics 2026-05-28 Wonyoung Kim , Min-Hwan Oh , Garud Iyengar , Assaf Zeevi

Modern deep learning methods provide effective means to learn good representations. However, is a good representation itself sufficient for sample efficient reinforcement learning? This question has largely been studied only with respect to…

Machine Learning · Computer Science 2020-03-02 Simon S. Du , Sham M. Kakade , Ruosong Wang , Lin F. Yang

Motivated by the success of reinforcement learning (RL) for discrete-time tasks such as AlphaGo and Atari games, there has been a recent surge of interest in using RL for continuous-time control of physical systems (cf. many challenging…

Optimization and Control · Mathematics 2018-12-03 Motoya Ohnishi , Masahiro Yukawa , Mikael Johansson , Masashi Sugiyama

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Machine Learning · Computer Science 2020-11-20 Jonathan N. Lee , Aldo Pacchiano , Vidya Muthukumar , Weihao Kong , Emma Brunskill

Motivated by conforming finite element methods for elliptic problems of second order, we analyze the approximation of the gradient of a target function by continuous piecewise polynomial functions over a simplicial mesh. The main result is…

Numerical Analysis · Mathematics 2018-03-07 Andreas Veeser

The integration of reinforcement learning (RL) into large language models (LLMs) has opened new opportunities for recommender systems by eliciting reasoning and improving user preference modeling. However, RL-based LLM recommendation faces…

Information Retrieval · Computer Science 2026-02-05 Lin Wang , Yang Zhang , Jingfan Chen , Xiaoyan Zhao , Fengbin Zhu , Qing Li , Tat-Seng Chua

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

We propose a new numerical scheme for approximating level-sets of Lipschitz multivariate functions which is robust to stochastic noise. The algorithm's main feature is an adaptive grid-based stochastic approximation strategy which…

Numerical Analysis · Mathematics 2025-09-19 Matteo Croci , Abdul-Lateef Haji-Ali , Ian C. J. Powell

Data valuation has found various applications in machine learning, such as data filtering, efficient learning and incentives for data sharing. The most popular current approach to data valuation is the Shapley value. While popular for its…

Machine Learning · Computer Science 2023-11-10 Lauren Watson , Zeno Kujawa , Rayna Andreeva , Hao-Tsung Yang , Tariq Elahi , Rik Sarkar

In tabular multi-agent reinforcement learning with average-cost criterion, a team of agents sequentially interacts with the environment and observes local incentives. We focus on the case that the global reward is a sum of local rewards,…

Optimization and Control · Mathematics 2021-10-26 Alec Koppel , Amrit Singh Bedi , Bhargav Ganguly , Vaneet Aggarwal

Reinforcement learning has achieved great success in many decision-making tasks, and traditional reinforcement learning algorithms are mainly designed for obtaining a single optimal solution. However, recent works show the importance of…

Machine Learning · Computer Science 2023-08-24 Fanqi Lin , Shiyu Huang , Weiwei Tu

We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics. Unlike existing growing methods, which follow simple…

Machine Learning · Computer Science 2023-06-23 Xin Yuan , Pedro Savarese , Michael Maire

Multi-fidelity Reinforcement Learning (RL) frameworks efficiently utilize computational resources by integrating analysis models of varying accuracy and costs. The prevailing methodologies, characterized by transfer learning, human-inspired…

Machine Learning · Computer Science 2025-03-25 Akash Agrawal , Christopher McComb

Value-function-based methods have long played an important role in reinforcement learning. However, finding the best next action given a value function of arbitrary complexity is nontrivial when the action space is too large for…

Machine Learning · Computer Science 2020-10-26 Arthur Delarue , Ross Anderson , Christian Tjandraatmadja

Following a recent surge in using history-based methods for resolving perceptual aliasing in reinforcement learning, we introduce an algorithm based on the feature reinforcement learning framework called PhiMDP. To create a practical…

Artificial Intelligence · Computer Science 2011-08-19 Phuong Nguyen , Peter Sunehag , Marcus Hutter

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of…

Machine Learning · Statistics 2015-05-20 Alhussein Fawzi , Mathieu Sinn , Pascal Frossard

We propose a procedure to build a decision tree which approximates the performance of complex machine learning models. This single approximation tree can be used to interpret and simplify the predicting pattern of random forests (RFs) and…

Methodology · Statistics 2016-10-31 Yichen Zhou , Giles Hooker

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

‹ Prev 1 4 5 6 7 8 10 Next ›