지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 한국정보처리학회 JIPS(Journal of Information Processing Systems) JIPS(Journal of Information Processing Systems) 제8권 제3호
- 발행연도
- 2012.1
- 수록면
- 409 - 420 (12page)
이용수
초록· 키워드
오류제보하기
The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions.
However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method.
Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.
목차
등록된 정보가 없습니다.
참고문헌 (13)
참고문헌 신청
A. Cypher / 1993 / Watch What I Do: Programming by Demonstration / MIT Press
A. Mcgovern / 1997 / Roles of Macro-Actions in Accelerating Reinforcement Learning / Proceedings of Grace Hopper Celebration of Women in Computing, San Jose, CA : 13 ~ 18
F. S. Melo / 2007 / Q-learning with Linear Function Approximation / Lecture Notes in Artificial Intelligence (LNAI) 4539 : 308 ~ 322
J. Randløv / 1999 / Learning Macro-actions in Reinforcement Learning / University of Copenhagen
M. J Matari? / 2000 / Imitation in Animals and Artifacts : Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics / MIT Press : 391 ~ 42
A. Mcgovern / 1997 / Roles of Macro-Actions in Accelerating Reinforcement Learning / Proceedings of Grace Hopper Celebration of Women in Computing, San Jose, CA : 13 ~ 18
F. S. Melo / 2007 / Q-learning with Linear Function Approximation / Lecture Notes in Artificial Intelligence (LNAI) 4539 : 308 ~ 322
J. Randløv / 1999 / Learning Macro-actions in Reinforcement Learning / University of Copenhagen
M. J Matari? / 2000 / Imitation in Animals and Artifacts : Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics / MIT Press : 391 ~ 42
이 논문의 저자 정보
최근 본 자료
댓글(0)
0