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 -