Apprenticeship Learning for Model Parameters of Partially Observable Environments

DOI Web Site 参考文献19件 オープンアクセス

書誌事項

タイトル別名
  • 部分観測環境のモデルパラメータに対する徒弟学習
  • ブブン カンソク カンキョウ ノ モデルパラメータ ニ タイスル トテイ ガクシュウ
  • 情報論的学習理論と機械学習
  • ジョウホウロンテキ ガクシュウ リロン ト キカイ ガクシュウ

この論文をさがす

説明

We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialogue system. We show that we can extract information about the environment model by inferring action selection process behind the demonstration, under the assumption that the expert is choosing optimal actions based on knowledge of the true model of the target environment. Proposed algorithms can achieve more accurate estimates of POMDP parameters and better policies from a short demonstration, compared to methods that learns only from the reaction from the environment.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

収録刊行物

参考文献 (19)*注記

もっと見る

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ