A Computational Model of an Instruction Learner: How to Learn “good” or “bad” through Action
-
- Suzuki Kentaro
- The University of Tokyo
-
- Ueda Kazuhiro
- The University of Tokyo
-
- Hiraki Kazuo
- The University of Tokyo JST, Presto
Bibliographic Information
- Other Title
-
- 自律的な行動学習を利用した評価教示の計算論的意味学習モデル
- ジリツテキ ナ コウドウ ガクシュウ オ リヨウ シタ ヒョウカ キョウジ ノ ケイサンロンテキ イミ ガクシュウ モデル
Search this article
Description
This paper proposes a model that can learn the meanings of instructions (for example, “good” and “bad”.). This model assumes that an advisee learns the meanings of instructions in parallel with learning the evaluation of its action experience. The reinforcement learning algorithm is adopted for the action learning. We conducted experiments with a robot simulator. The result of the experiments suggests that our model can learn not only evaluation-instructions but also two types of instruction (evaluation-instructions and direction-instructions) simultaneously. This model can be thought as a basic model of an intelligent agent that can learn the meanings of instructions.
Journal
-
- Cognitive Studies: Bulletin of the Japanese Cognitive Science Society
-
Cognitive Studies: Bulletin of the Japanese Cognitive Science Society 9 (2), 200-212, 2002
Japanese Cognitive Science Society
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679461404288
-
- NII Article ID
- 10009707739
-
- NII Book ID
- AN1047304X
-
- ISSN
- 18815995
- 13417924
-
- NDL BIB ID
- 025100141
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
-
- Abstract License Flag
- Disallowed