SJ Gershman - Journal of Mathematical Psychology, 2016 - Elsevier
… Computational models of reinforcementlearning have played an important role in understanding learning and decision making behavior, as well as the neural mechanisms underlying …
… reinforcementlearning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning… to a need for standardized empiricalanalyses. Our …
Q Liu, T Yu, Y Bai, C Jin - … Conference on Machine Learning, 2021 - proceedings.mlr.press
… This paper is concerned with the problem of multi-agent reinforcementlearning (multi-agent RL), in which multiple agents learn to make decisions in an unknown environment in order …
… Since their introduction a year ago, distributional approaches to reinforcementlearning (… We then continue with an empiricalanalysis comparing distributional and expected RL …
… We consider the standard reinforcementlearning formalism consisting of an agent interacting with an environment. To simplify the exposition we assume in this section that the …
A Anderson, J Dodge, A Sadarangani… - arXiv preprint arXiv …, 2019 - arxiv.org
… And perhaps most critical, one type of empiricalanalysis (strictly quantitative or strictly qualitative… an arsenal of empirical techniques, can we gain the rich insights needed to learn how to …
C Voloshin, HM Le, Y Yue - Real-world Sequential Decision …, 2019 - realworld-sdm.github.io
… In this paper, we present the first comprehensive empiricalanalysis of most of the recently proposed OPE methods. Based on thousands of experiments and detailed empirical analyses, …
Y Li - arXiv preprint arXiv:1701.07274, 2017 - arxiv.org
… We give an overview of recent exciting achievements of deep reinforcementlearning (RL). … We start with background of machine learning, deep learning and reinforcementlearning. …
… We present a distributional approach to theoretical analyses of reinforcementlearning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and …