書誌事項
- タイトル別名
-
- Cognitive Distance Learning Problem Solver Reduces Search Cost through Learning Processes
- ニンチ キョリ ガクシュウ ニ ヨル モンダイ カイケツキ ノ ジッコウジ タンサク サクゲン ノ ヒョウカ ト ガクシュウ プロセス ノ カイセキ
この論文をさがす
説明
Our proposed cognitive distance learning problem solver generates sequence of actions from initial state to goal states in problem state space. This problem solver learns cognitive distance (path cost) of arbitrary combination of two states. Action generation at each state is selection of next state that has minimum cognitive distance to the goal, like Q-learning agent. In this paper, first, we show that our proposed method reduces search cost than conventional search method by analytical simulation in spherical state space. Second, we show that an average search cost is more reduced more the prior learning term is long and our problem solver is familiar to the environment, by a computer simulation in a tile world state space. Third, we showed that proposed problem solver is superior to the reinforcement learning techniques when goal is changed by a computer simulation. Forth, we found that our simulation result consist with psychological experimental results.
収録刊行物
-
- 人工知能学会論文誌
-
人工知能学会論文誌 17 1-13, 2002
一般社団法人 人工知能学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282680083491328
-
- NII論文ID
- 10015770557
-
- NII書誌ID
- AA11579226
-
- ISSN
- 13468030
- 13460714
-
- NDL書誌ID
- 6446826
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- NDLサーチ
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可
