Autonomous self-explanation of behavior for interactive reinforcement learning agents

Yosuke Fukuchi; Masahiko Osawa; Hiroshi Yamakawa; Michita Imai

doi:10.1145/3125739.3125746

Autonomous self-explanation of behavior for interactive reinforcement learning agents

Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Michita Imai

Department of Information and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent's future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent's policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity.

Original language	English
Title of host publication	HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction
Publisher	Association for Computing Machinery, Inc
Pages	97-101
Number of pages	5
ISBN (Electronic)	9781450351133
DOIs	https://doi.org/10.1145/3125739.3125746
Publication status	Published - 2017 Oct 17
Event	5th International Conference on Human Agent Interaction, HAI 2017 - Bielefeld, Germany Duration: 2017 Oct 17 → 2017 Oct 20

Publication series

Name	HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction

Other

Other	5th International Conference on Human Agent Interaction, HAI 2017
Country	Germany
City	Bielefeld
Period	17/10/17 → 17/10/20

Keywords

Human Robot Cooperation
Instruction-based Behavior Explanation
Interactive Reinforcement Learning

ASJC Scopus subject areas

Human-Computer Interaction

Access to Document

10.1145/3125739.3125746

Fingerprint Dive into the research topics of 'Autonomous self-explanation of behavior for interactive reinforcement learning agents'. Together they form a unique fingerprint.

Cite this

Fukuchi, Y., Osawa, M., Yamakawa, H., & Imai, M. (2017). Autonomous self-explanation of behavior for interactive reinforcement learning agents. In HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction (pp. 97-101). (HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction). Association for Computing Machinery, Inc. https://doi.org/10.1145/3125739.3125746

Autonomous self-explanation of behavior for interactive reinforcement learning agents. / Fukuchi, Yosuke; Osawa, Masahiko; Yamakawa, Hiroshi; Imai, Michita.

HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction. Association for Computing Machinery, Inc, 2017. p. 97-101 (HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Fukuchi, Y, Osawa, M, Yamakawa, H & Imai, M 2017, Autonomous self-explanation of behavior for interactive reinforcement learning agents. in HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction. HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction, Association for Computing Machinery, Inc, pp. 97-101, 5th International Conference on Human Agent Interaction, HAI 2017, Bielefeld, Germany, 17/10/17. https://doi.org/10.1145/3125739.3125746

Fukuchi Y, Osawa M, Yamakawa H, Imai M. Autonomous self-explanation of behavior for interactive reinforcement learning agents. In HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction. Association for Computing Machinery, Inc. 2017. p. 97-101. (HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction). https://doi.org/10.1145/3125739.3125746

Fukuchi, Yosuke ; Osawa, Masahiko ; Yamakawa, Hiroshi ; Imai, Michita. / Autonomous self-explanation of behavior for interactive reinforcement learning agents. HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction. Association for Computing Machinery, Inc, 2017. pp. 97-101 (HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction).

@inproceedings{4a8f282e13cf4dbcad1419922e177d70,

title = "Autonomous self-explanation of behavior for interactive reinforcement learning agents",

abstract = "In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent's future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent's policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity.",

keywords = "Human Robot Cooperation, Instruction-based Behavior Explanation, Interactive Reinforcement Learning",

author = "Yosuke Fukuchi and Masahiko Osawa and Hiroshi Yamakawa and Michita Imai",

year = "2017",

month = oct,

day = "17",

doi = "10.1145/3125739.3125746",

language = "English",

series = "HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction",

publisher = "Association for Computing Machinery, Inc",

pages = "97--101",

booktitle = "HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction",

note = "5th International Conference on Human Agent Interaction, HAI 2017 ; Conference date: 17-10-2017 Through 20-10-2017",

}

TY - GEN

T1 - Autonomous self-explanation of behavior for interactive reinforcement learning agents

AU - Fukuchi, Yosuke

AU - Osawa, Masahiko

AU - Yamakawa, Hiroshi

AU - Imai, Michita

PY - 2017/10/17

Y1 - 2017/10/17

N2 - In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent's future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent's policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity.

AB - In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent's future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent's policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity.

KW - Human Robot Cooperation

KW - Instruction-based Behavior Explanation

KW - Interactive Reinforcement Learning

UR - http://www.scopus.com/inward/record.url?scp=85034862370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034862370&partnerID=8YFLogxK

U2 - 10.1145/3125739.3125746

DO - 10.1145/3125739.3125746

M3 - Conference contribution

AN - SCOPUS:85034862370

T3 - HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction

SP - 97

EP - 101

BT - HAI 2017 - Proceedings of the 5th International Conference on Human Agent Interaction

PB - Association for Computing Machinery, Inc

T2 - 5th International Conference on Human Agent Interaction, HAI 2017

Y2 - 17 October 2017 through 20 October 2017

ER -