Sciweavers

27 search results - page 1 / 6
» Efficient Behavior Learning Based on State Value Estimation ...
Sort
View
AR
2008
118views more  AR 2008»
13 years 3 months ago
Efficient Behavior Learning Based on State Value Estimation of Self and Others
The existing reinforcement learning methods have been seriously suffering from the curse of dimension problem especially when they are applied to multiagent dynamic environments. ...
Yasutake Takahashi, Kentarou Noma, Minoru Asada
ROBOCUP
2007
Springer
167views Robotics» more  ROBOCUP 2007»
13 years 9 months ago
Cooperative/Competitive Behavior Acquisition Based on State Value Estimation of Others
The existing reinforcement learning approaches have been suffering from the curse of dimension problem when they are applied to multiagent dynamic environments. One of the typical...
Kentarou Noma, Yasutake Takahashi, Minoru Asada
IROS
2007
IEEE
164views Robotics» more  IROS 2007»
13 years 10 months ago
Emulation and behavior understanding through shared values
— Neurophysiology has revealed the existence of mirror neurons in brain of macaque monkeys and they shows similar activities during executing an observation of goal directed move...
Yasutake Takahashi, Teruyasu Kawamata, Minoru Asad...
IROS
2008
IEEE
165views Robotics» more  IROS 2008»
13 years 10 months ago
Mutual development of behavior acquisition and recognition based on value system
Abstract. Both self-learning architecture (embedded structure) and explicit/implicit teaching from other agents (environmental design issue) are necessary not only for one behavior...
Yasutake Takahashi, Yoshihiro Tamura, Minoru Asada
ISER
2004
Springer
143views Robotics» more  ISER 2004»
13 years 9 months ago
Imitation Learning Based on Visuo-Somatic Mapping
Abstract. Imitation learning is a powerful approach to humanoid behavior generation, however, the most existing methods assume the availability of the information on the internal s...
Minoru Asada, Masaki Ogino, Shigeo Matsuyama, Jun'...