Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Guez, A; Silver, D; Dayan, P

Local TagsRelease HistoryDetailsSummary

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Guez, A., Silver, D., & Dayan, P. (2013). Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search. In P. Bartlett, F. Pereira, L. Bottou, C. Burgess, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems 25 (pp. 1025-1033). Red Hook, NY, USA: Curran.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/21.11116/0000-0004-C38C-2 Version Permalink: https://hdl.handle.net/21.11116/0000-0004-C38D-1

Genre: Conference Paper

Files

show Files

Locators

show

hide

Locator:
http://papers.nips.cc/paper/4767-efficient-bayes-adaptive-reinforcement-learning-using-sample-based-search.pdf (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Guez, A, Author
Silver, D, Author
Dayan, P¹, Author

Affiliations:
1External Organizations, ou_persistent22

Content

show

hide

Free keywords: -

Abstract: Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal policies is notoriously taxing, since the search space becomes enormous. In this paper we introduce a tractable, sample-based method for approximate Bayes-optimal planning which exploits Monte-Carlo tree search. Our approach outperformed prior Bayesian model-based RL algorithms by a significant margin on several well-known benchmark problems -- because it avoids expensive applications of Bayes rule within the search tree by lazily sampling models from the current beliefs. We illustrate the advantages of our approach by showing it working in an infinite state space domain which is qualitatively out of reach of almost all previous work in Bayesian exploration.

Details

show

hide

Language(s):

Dates: Date issued: 2013-04

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: -

Degree: -

Event

show

hide

Title: Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012)

Place of Event: Lake Tahoe, NV, USA

Start-/End Date: 2012-12-03 - 2012-12-06

Legal Case

show

Project information

show

Source 1

show

hide

Title: Advances in Neural Information Processing Systems 25

Source Genre: Proceedings

Creator(s):
Bartlett, P, Editor
Pereira, FCN, Editor
Bottou, L, Editor
Burgess, CJC, Editor
Weinberger, KQ, Editor

Affiliations:
-

Publ. Info: Red Hook, NY, USA : Curran

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1025 - 1033 Identifier: ISBN: 978-1-62748-003-1