書誌事項
- タイトル別名
-
- TCS; Time-dependent Classifier System for solving perceptual aliasing problems
- フカンゼン チカク モンダイ カイケツ ノ タメ ノ ジケイレツ イゾン ブンルイ システム TCS ノ テイアン
この論文をさがす
抄録
Recently, many works about Partially Observable Markov Decision Processes have attracted increasing attentions in reinforcement learning because the world cannot be always modeled on Markov Decision Processes. In this paper, Time-dependent Classifier System; TCS is proposed to solve perceptual aliasing problems. In TCS, it keeps the constant length of time sequential information, and uses them only when it is necessary to solve the perceptual aliasing. So, the changeable lengths of rules are proposed in TCS using the time tags. And the internal action to detect the information of 1 time-step is used to link the present information to the past information. And the several maze problems with Partially Observable Markov Decision Processes are experimented to verify TCS's effectiveness.
収録刊行物
-
- 電気学会論文誌C(電子・情報・システム部門誌)
-
電気学会論文誌C(電子・情報・システム部門誌) 122 (7), 1218-1225, 2002
一般社団法人 電気学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282679586557568
-
- NII論文ID
- 130006845133
- 10008844494
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 6204812
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可