English
Related papers

Related papers: Unifying Gradient Estimators for Meta-Reinforcemen…

200 papers

We propose a novel hybrid stochastic policy gradient estimator by combining an unbiased policy gradient estimator, the REINFORCE estimator, with another biased one, an adapted SARAH estimator for policy optimization. The hybrid policy…

Machine Learning · Computer Science 2020-09-23 Nhan H. Pham , Lam M. Nguyen , Dzung T. Phan , Phuong Ha Nguyen , Marten van Dijk , Quoc Tran-Dinh

Decision trees are ubiquitous in machine learning for their ease of use and interpretability. Yet, these models are not typically employed in reinforcement learning as they cannot be updated online via stochastic gradient descent. We…

Machine Learning · Computer Science 2020-06-29 Andrew Silva , Taylor Killian , Ivan Dario Jimenez Rodriguez , Sung-Hyun Son , Matthew Gombolay

Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model. However, the estimation and classifier…

Machine Learning · Computer Science 2020-09-01 Tianyu Li , Chien-Chih Wang , Yukun Ma , Patricia Ortal , Qifang Zhao , Bjorn Stenger , Yu Hirate

Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn value predictors from data is one of the major problems studied by the RL community, and different approaches…

Machine Learning · Computer Science 2020-10-22 Arthur Guez , Fabio Viola , Théophane Weber , Lars Buesing , Steven Kapturowski , Doina Precup , David Silver , Nicolas Heess

In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is…

Machine Learning · Computer Science 2019-05-09 Yiming Shen , Kehan Yang , Yufeng Yuan , Simon Cheng Liu

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic…

Machine Learning · Computer Science 2017-08-15 Riashat Islam , Peter Henderson , Maziar Gomrokchi , Doina Precup

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

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

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

Differentiable simulators promise faster computation time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients. However, it is yet unclear what…

Machine Learning · Computer Science 2022-08-23 H. J. Terry Suh , Max Simchowitz , Kaiqing Zhang , Russ Tedrake

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and…

Machine Learning · Computer Science 2013-01-14 Lex Weaver , Nigel Tao

This paper studies off-policy evaluation (OPE) in the presence of unmeasured confounders. Inspired by the two-way fixed effects regression model widely used in the panel data literature, we propose a two-way unmeasured confounding…

Machine Learning · Computer Science 2024-12-10 Shuguang Yu , Shuxing Fang , Ruixin Peng , Zhengling Qi , Fan Zhou , Chengchun Shi

Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias…

Machine Learning · Computer Science 2018-02-01 Roy Fox , Ari Pakman , Naftali Tishby

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve…

Machine Learning · Computer Science 2018-05-01 Rein Houthooft , Richard Y. Chen , Phillip Isola , Bradly C. Stadie , Filip Wolski , Jonathan Ho , Pieter Abbeel

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly…

Artificial Intelligence · Computer Science 2013-04-16 Matthieu Geist , Bruno Scherrer

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the…

Machine Learning · Statistics 2015-04-03 Dougal Maclaurin , David Duvenaud , Ryan P. Adams

In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learning scheme based on variational inference. This scheme is…

Machine Learning · Computer Science 2019-07-12 Markus Kaiser , Clemens Otte , Thomas Runkler , Carl Henrik Ek

Reconstructing force fields (FFs) from atomistic simulation data is a challenge since accurate data can be highly expensive. Here, machine learning (ML) models can help to be data economic as they can be successfully constrained using the…

Chemical Physics · Physics 2022-10-27 Niklas Frederik Schmitz , Klaus-Robert Müller , Stefan Chmiela