Reinforcement Learning and the Bayesian Control Rule

Ortega, PA; Braun, DA

doi:10.1007/978-3-642-22887-2_30

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

会議論文

Reinforcement Learning and the Bayesian Control Rule

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

https://link.springer.com/content/pdf/10.1007%2F978-3-642-22887-2_30.pdf
(出版社版)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Ortega, P., & Braun, D. (2011). Reinforcement Learning and the Bayesian Control Rule. In S., Godsill, J., Schmidhuber, K., Thórisson, & M., Looks (Eds.), Artificial General Intelligence (pp. 281-285). Berlin, Germany: Springer.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-BADC-6

要旨

We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intractable planning problem reduces to a simple multi-armed bandit problem, where each lever stands for a potentially arbitrarily complex policy. Furthermore, we use the Bayesian control rule to construct an adaptive bandit player that is universal with respect to a given class of optimal bandit players, thus indirectly constructing an adaptive agent that is universal with respect to a given class of policies.