Kobayashi, Shigenobu

10 publications

NeurIPS 2010 Natural Policy Gradient Methods with Parameter-Based Exploration for Control Tasks Atsushi Miyamae, Yuichi Nagata, Isao Ono, Shigenobu Kobayashi

ICML 2008 Privacy-Preserving Reinforcement Learning Jun Sakuma, Shigenobu Kobayashi, Rebecca N. Wright

ICML 2001 Average-Reward Reinforcement Learning for Variance Penalized Markov Decision Problems Makoto Sato, Shigenobu Kobayashi

ICML 2000 A Universal Generalization for Temporal-Difference Learning Using Haar Basis Functions Susumu Katayama, Hajime Kimura, Shigenobu Kobayashi

ICML 1999 Efficient Non-Linear Control by Combining Q-Learning with Local Linear Controllers Hajime Kimura, Shigenobu Kobayashi

ICML 1998 An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function Hajime Kimura, Shigenobu Kobayashi

ICML 1997 Reinforcement Learning in POMDPs with Function Approximation Hajime Kimura, Kazuteru Miyazaki, Shigenobu Kobayashi

ICML 1995 Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward Hajime Kimura, Masayuki Yamamura, Shigenobu Kobayashi

ALT 1993 Algorithmic Learning Theory, 4th International Workshop, ALT '93, Tokyo, Japan, November 8-10, 1993, Proceedings Klaus P. Jantke, Shigenobu Kobayashi, Etsuji Tomita, Takashi Yokomori

IJCAI 1991 An Augmented EBL and Its Application to the Utility Problem Masayuki Yamamura, Shigenobu Kobayashi