English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Static and Dynamic Values of Computation in MCTS

Sezener, E., & Dayan, P. (2020). Static and Dynamic Values of Computation in MCTS. Red Hook, NY, USA: Curran.

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Sezener, E, Author
Dayan, P1, 2, Author              
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Monte-Carlo Tree Search (MCTS) is one of the most-widely used methodsfor planning, and has powered many recent advances in artificialintelligence. In MCTS, one typically performs computations(i.e., simulations) to collect statistics about the possible futureconsequences of actions, and then chooses accordingly. Manypopular MCTS methods such as UCT and its variants decide whichcomputations to perform by trading-off exploration and exploitation. Inthis work, we take a more direct approach, and explicitly quantify thevalue of a computation based on its expected impact on the quality ofthe action eventually chosen. Our approach goes beyond the \emph{myopic}limitations of existing computation-value-based methods in two senses:(I) we are able to account for the impact of non-immediate (ie, future)computations (II) on non-immediate actions. We show that policies thatgreedily optimize computation values are optimal under certainassumptions and obtain results that are competitive with the state-of-the-art.

Details

show
hide
Language(s):
 Dates: 2020-08
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: 36th Conference on Uncertainty in Artificial Intelligence (UAI 2020)
Place of Event: -
Start-/End Date: 2020-08-03 - 2020-08-06

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of Machine Learning Research (PMLR)
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: Red Hook, NY, USA : Curran
Pages: - Volume / Issue: 124 Sequence Number: 26 Start / End Page: 31 - 40 Identifier: -