Classifying the Strategies of an Opponent Team Based on a Sequence of Actions in the RoboCup SSL

Adachi, Yusuke; Ito, Masahide; Naruse, Tadashi

doi:10.1007/978-3-319-68792-6_9

Cited by 8 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In particular, an action sequence composed of actions directly expresses what happens during the game. The algorithms developed in our previous studies [7,8] basically work by extracting actions from geometric data sets. However, one of these previous methods [8] is limited to offline clustering, and such a method could be employed for dominating the game.…”

mentioning

confidence: 99%

“…The algorithms developed in our previous studies [7,8] basically work by extracting actions from geometric data sets. However, one of these previous methods [8] is limited to offline clustering, and such a method could be employed for dominating the game. By extending the algorithms in [8], this paper newly proposes an online strategy clustering method based on action sequences.…”

mentioning

confidence: 99%

“…However, one of these previous methods [8] is limited to offline clustering, and such a method could be employed for dominating the game. By extending the algorithms in [8], this paper newly proposes an online strategy clustering method based on action sequences. The performance of our proposed method was evaluated through some experiments for both offline and online cases.…”

mentioning

confidence: 99%

“…Our previous work [8] already adopted action sequences as a clustering data set, but was NOT applicable to online clustering.…”

mentioning

confidence: 99%

“…To the best of the authors' knowledge, a strategy clustering method that utilizes action sequences has not been reported so far, except for [8]. Table 1.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Online Strategy Clustering Based on Action Sequences in RoboCupSoccer Small Size League

Adachi¹,

Ito²,

Naruse³

2019

Robotics

Self Cite

View full text Add to dashboard Cite

This paper addresses a strategy learning problem in the RoboCupSoccer Small Size League (SSL). We propose a novel method based on action sequences to cluster an opponent’s strategies online. Our proposed method is composed of the following three steps: (1) extracting typical actions from geometric data to make action sequences, (2) calculating the dissimilarity of the sequences, and (3) clustering the sequences by using the dissimilarity. This method can reduce the amount of data used in the clustering process; handling action sequences instead of geometric data as data-set makes it easier to search actions. As a result, the proposed clustering method is online feasible and also is applicable to countering an opponent’s strategy. The effectiveness of the proposed method was validated by experimental results.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

“…Our previous work [8] already adopted action sequences as a clustering data set, but was NOT applicable to online clustering.…”

mentioning

confidence: 99%

“…To the best of the authors' knowledge, a strategy clustering method that utilizes action sequences has not been reported so far, except for [8]. Table 1.…”

mentioning

confidence: 99%

See 3 more Smart Citations