強化学習を用いた自律移動型ロボットの行動計画法の提案

Transactions of the Japanese Society for Artificial Intelligence 16:501-509 (2001)
  Copy   BIBTEX

Abstract

In a previous paper, we proposed a solution to navigation of a mobile robot. In our approach, we formulated the following two problems at each time step as discrete optimization problems: 1) estimation of position and direction of a robot, and 2)action decision. While the results of our simulation showed the effectiveness of our approach, the values of weights in the objective functions were given by a heuristic method. This paper presents a theoretical method using reinforcement learning for adjusting the weight parameters in the objective function that includes pieces of heuristic knowledge on the action decision. In our reinforcement learning, the expectation of a reward given to a robot’s trajectory is defined as the value function to maximize. The robot’s trajectories are generated stochastically because we used a probabilistic policy for determining actions of a robot to search for the global optimal trajectory. However, this decision process is not a Markov decision process because the objective function includes an action at the previous time. Thus, Q-learning, which is a conventional method of reinforcement learning, cannot be applied to this problem. In this paper, we applied Williams’s episodic REINFORCE approach to the action decision and derived a learning rule for the weight parameters of the objective function. Moreover, we applied the stochastic hill-climbing method to maximizing the value function to reduce computation time. The learning rule was verified by our experiment.

Other Versions

No versions found

Links

PhilArchive

    This entry is not archived by us. If you are the author and have permission from the publisher, we recommend that you archive it. Many publishers automatically grant permission to authors to archive pre-prints. By uploading a copy of your work, you will enable us to better index it, making it easier to find.

    Upload a copy of this work     Papers currently archived: 102,141

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

尤度情報に基づく温度分布を用いた強化学習法.鈴木 健嗣 小堀 訓成 - 2005 - Transactions of the Japanese Society for Artificial Intelligence 20:297-305.
Qdsega による多足ロボットの歩行運動の獲得.Matsuno Fumitoshi Ito Kazuyuki - 2002 - Transactions of the Japanese Society for Artificial Intelligence 17:363-372.
経験に固執しない Profit Sharing 法.Ueno Atsushi Uemura Wataru - 2006 - Transactions of the Japanese Society for Artificial Intelligence 21:81-93.
Profit Sharing 法における強化関数に関する一考察.Tatsumi Shoji Uemura Wataru - 2004 - Transactions of the Japanese Society for Artificial Intelligence 19:197-203.
強化学習エージェントへの階層化意志決定法の導入―追跡問題を例に―.輿石 尚宏 謙吾 片山 - 2004 - Transactions of the Japanese Society for Artificial Intelligence 19:279-291.
Ga により探索空間の動的生成を行う Q 学習.Matsuno Fumitoshi Ito Kazuyuki - 2001 - Transactions of the Japanese Society for Artificial Intelligence 16:510-520.
Κ-確実探査法と動的計画法を用いた mdps 環境の効率的探索法.Kawada Seiichi Tateyama Takeshi - 2001 - Transactions of the Japanese Society for Artificial Intelligence 16:11-19.
罰を回避する合理的政策の学習.坪井 創吾 宮崎 和光 - 2001 - Transactions of the Japanese Society for Artificial Intelligence 16 (2):185-192.

Analytics

Added to PP
2014-03-25

Downloads
28 (#815,434)

6 months
10 (#441,927)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations

References found in this work

No references found.

Add more references