English
Related papers

Related papers: Deep Bayesian Quadrature Policy Optimization

200 papers

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a…

Machine Learning · Computer Science 2017-04-11 Yang Liu , Prajit Ramachandran , Qiang Liu , Jian Peng

We propose a gradient-free deep reinforcement learning algorithm to solve high-dimensional, finite-horizon stochastic control problems. Although the recently developed deep reinforcement learning framework has achieved great success in…

Optimization and Control · Mathematics 2025-02-03 Liyao Lyu , Jingrun Chen

Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. Monte Carlo tree search with progressive widening attempts to improve scaling by sampling from the action space…

Artificial Intelligence · Computer Science 2021-11-04 John Mern , Anil Yildiz , Zachary Sunberg , Tapan Mukerji , Mykel J. Kochenderfer

In this paper we propose a new deterministic approximation method, called discretization approximation, for Bayesian computation. Discretization approximation is very simple to understand and to implement, It only requires calculating…

Computation · Statistics 2026-01-13 Shifeng Xiong

In this paper, we investigate a model-free optimal control design that minimizes an infinite horizon average expected quadratic cost of states and control actions subject to a probabilistic risk or chance constraint using input-output data.…

Systems and Control · Electrical Eng. & Systems 2024-11-11 Arunava Naha , Subhrakanti Dey

Multilevel Monte Carlo is a key tool for approximating integrals involving expensive scientific models. The idea is to use approximations of the integrand to construct an estimator with improved accuracy over classical Monte Carlo. We…

Methodology · Statistics 2023-03-15 Kaiyu Li , Daniel Giles , Toni Karvonen , Serge Guillas , François-Xavier Briol

We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct a more efficient and accurate gradient estimator. The…

Machine Learning · Computer Science 2021-06-25 Samuel Ainsworth , Kendall Lowrey , John Thickstun , Zaid Harchaoui , Siddhartha Srinivasa

This study introduces a computationally efficient algorithm, delayed acceptance Markov chain Monte Carlo (DA-MCMC), designed to improve posterior simulation in quasi-Bayesian inference. Quasi-Bayesian methods, which do not require fully…

Computation · Statistics 2026-02-16 Masahiro Tanaka

We introduce BayeSQP, a novel algorithm for general black-box optimization that merges the structure of sequential quadratic programming with concepts from Bayesian optimization. BayeSQP employs second-order Gaussian process surrogates for…

Machine Learning · Computer Science 2026-02-04 Paul Brunzema , Sebastian Trimpe

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies.…

Machine Learning · Computer Science 2020-08-14 Alekh Agarwal , Mikael Henaff , Sham Kakade , Wen Sun

Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical…

Machine Learning · Computer Science 2026-05-08 Hyunjun Na , Donghwan Lee

We propose a Monte Carlo algorithm to sample from high dimensional probability distributions that combines Markov chain Monte Carlo and importance sampling. We provide a careful theoretical analysis, including guarantees on robustness to…

Computation · Statistics 2019-09-18 Giacomo Zanella , Gareth Roberts

In this paper we propose an efficient stochastic optimization algorithm to search for Bayesian experimental designs such that the expected information gain is maximized. The gradient of the expected information gain with respect to…

Computation · Statistics 2022-02-03 Takashi Goda , Tomohiko Hironaka , Wataru Kitade , Adam Foster

This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly,…

Machine Learning · Computer Science 2016-11-18 Christos Dimitrakakis

Bayesian quadrature (BQ) is a method for solving numerical integration problems in a Bayesian manner, which allows users to quantify their uncertainty about the solution. The standard approach to BQ is based on a Gaussian process (GP)…

Methodology · Statistics 2021-12-03 Harrison Zhu , Xing Liu , Ruya Kang , Zhichao Shen , Seth Flaxman , François-Xavier Briol

The generation of decision-theoretic Bayesian optimal designs is complicated by the significant computational challenge of minimising an analytically intractable expected loss function over a, potentially, high-dimensional design space. A…

Methodology · Statistics 2017-02-07 Antony M. Overstall , James M. McGree , Christopher C. Drovandi

A novel efficient method for computing the Knowledge-Gradient policy for Continuous Parameters (KGCP) for deterministic optimization is derived. The differences with Expected Improvement (EI), a popular choice for Bayesian optimization of…

Computational Engineering, Finance, and Science · Computer Science 2016-08-17 Joachim van der Herten , Ivo Couckuyt , Dirk Deschrijver , Tom Dhaene

Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions. However, unlike most optimization methods, Bayesian optimization typically does not use derivative information. In…

Machine Learning · Statistics 2018-02-08 Jian Wu , Matthias Poloczek , Andrew Gordon Wilson , Peter I. Frazier

This paper addresses the challenging computational problem of estimating intractable expectations over discrete domains. Existing approaches, including Monte Carlo and Russian Roulette estimators, are consistent but often require a large…

Machine Learning · Statistics 2025-12-19 Sophia Seulkee Kang , François-Xavier Briol , Toni Karvonen , Zonghao Chen

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches…

Machine Learning · Computer Science 2022-06-20 Tom Blau , Edwin V. Bonilla , Iadine Chades , Amir Dezfouli