Invention Grant
- Patent Title: Reinforcement learning apparatus, control apparatus, and reinforcement learning method
- Patent Title (中): 加强学习装置，控制装置和强化学习方法
-
Application No.: US13432094Application Date: 2012-03-28
-
Publication No.: US08886357B2Publication Date: 2014-11-11
- Inventor: Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
- Applicant: Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
- Applicant Address: JP Kyoto JP Tokyo
- Assignee: Advanced Telecommunications Research Institute International,Honda Motor Co., Ltd.
- Current Assignee: Advanced Telecommunications Research Institute International,Honda Motor Co., Ltd.
- Current Assignee Address: JP Kyoto JP Tokyo
- Agency: Cermak Nakajima & McGowan LLP
- Agent Tomoko Nakajima
- Priority: JP2011-074694 20110330
- Main IPC: G06F19/00
- IPC: G06F19/00 ; G05B13/02
Abstract:
It is possible to perform robot motor learning in a quick and stable manner using a reinforcement learning apparatus including: a first-type environment parameter obtaining unit that obtains a value of one or more first-type environment parameters; a control parameter value calculation unit that calculates a value of one or more control parameters maximizing a reward by using the value of the one or more first-type environment parameters; a control parameter value output unit that outputs the value of the one or more control parameters to the control object; a second-type environment parameter obtaining unit that obtains a value of one or more second-type environment parameters; a virtual external force calculation unit that calculates the virtual external force by using the value of the one or more second-type environment parameters; and a virtual external force output unit that outputs the virtual external force to the control object.
Public/Granted literature
- US20120253514A1 REINFORCEMENT LEARNING APPARATUS, CONTROL APPARATUS, AND REINFORCEMENT LEARNING METHOD Public/Granted day:2012-10-04
Information query
