English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Towards a practical Bayes-optimal agent

Guez, A., Silver, D., & Dayan, P. (2013). Towards a practical Bayes-optimal agent. Poster presented at 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, NJ, USA.

Item is

Files

show Files

Locators

show
hide
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: Only rich and sophisticated statistical models are adequate for agents that must learn to navi- gate complex environments. However, it has not been clear how methods for planning can take advantage of models, such as those incorporating Bayesian non-parametric devices, that are sufficiently intricate as to demand approximate sampling schemes. We show that Bayes-Adaptive planning can be combined in a principled way with approximate sampling, and demonstrate the power of the resulting method in a chal- lenging task involving safe exploration which defeats myopic methods such as Thompson Sampling. This highlights the importance of propagating beliefs in realistic cases involving trade-offs between exploration and exploitation. The next challenge is to employ function approximation to represent the belief-state value to improve search efficiency further and thus enable longer search horizons.

Details

show
hide
Language(s):
 Dates: 2013-10
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013)
Place of Event: Princeton, NJ, USA
Start-/End Date: 2013-10-25 - 2013-10-27

Legal Case

show

Project information

show

Source 1

show
hide
Title: 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: F15 Start / End Page: 22 Identifier: -