2011
DOI: 10.2478/v10006-011-0057-3
|View full text |Cite
|
Sign up to set email alerts
|

Evolving small-board Go players using coevolutionary temporal difference learning with archives

Abstract: We apply Coevolutionary Temporal Difference Learning (CTDL) to learn small-board Go strategies represented as weighted piece counters. CTDL is a randomized learning technique which interweaves two search processes that operate in the intra-game and inter-game mode. Intra-game learning is driven by gradient-descent Temporal Difference Learning (TDL), a reinforcement learning method that updates the board evaluation function according to differences observed between its values for consecutively visited game stat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
10
0

Year Published

2012
2012
2021
2021

Publication Types

Select...
4
3

Relationship

3
4

Authors

Journals

citations
Cited by 12 publications
(10 citation statements)
references
References 32 publications
0
10
0
Order By: Relevance
“…In particular, we investigate how the size of the search space and the type of evaluation function influence the performance of evolutionary, coevolutionary, temporal difference learning (TDL) algorithms, and their hybrids introduced in our previous works [36], [15]. This allows us also to discuss the benefits of global and local search hybridization.…”
Section: Introductionmentioning
confidence: 99%
“…In particular, we investigate how the size of the search space and the type of evaluation function influence the performance of evolutionary, coevolutionary, temporal difference learning (TDL) algorithms, and their hybrids introduced in our previous works [36], [15]. This allows us also to discuss the benefits of global and local search hybridization.…”
Section: Introductionmentioning
confidence: 99%
“…Following other studies [16,6], we identify the computational effort with the number of games played in interactions among individuals.…”
Section: The Experimentsmentioning
confidence: 99%
“…Even though the archive mechanisms such as the Hall of Fame (HoF) [9,6,5] have been studied in the past and are known to maintain progress in an evolutionary arms race, they do not provide any specific guarantees in terms of convergence to the optimal solution. Moreover, the characteristics of archive's influence on evolving individuals is little known, which constitutes the main motivation for this study.…”
Section: Introductionmentioning
confidence: 99%