Title :
Intrinsically motivated anticipatory learning utilizing transformation invariance
Author :
Masuyama, Gakuto ; Yamashita, Atsushi ; Asama, Hajime
Author_Institution :
Univ. of Tokyo, Tokyo, Japan
Abstract :
In this paper, novel reinforcement learning framework with intrinsic motivation to reproduce past successful experience is presented. Geometric transformation invariance is utilized to measure the reproducibility of experience. Top-down “expectation” to reproducibility of experience effectively biases strategy of exploration. As a result of consistent exploration via reproduction of successful experience, learning process is accelerated. Simulation experiments in grid world demonstrate useful characteristics of proposed framework.
Keywords :
learning (artificial intelligence); robots; geometric transformation invariance; grid world; intrinsic motivation; intrinsically motivated anticipatory learning; reinforcement learning; Abstracts; Acceleration; Feature extraction; Information processing; Learning; Robot sensing systems;
Conference_Titel :
Development and Learning and Epigenetic Robotics (ICDL), 2012 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4673-4964-2
Electronic_ISBN :
978-1-4673-4963-5
DOI :
10.1109/DevLrn.2012.6400873
