Coaching Robots: Online Behavior Learning from Human Subjective Feedback
作者： Masakazu Hirkoawa , Kenji Suzuki
DOI: 10.1007/978-3-642-32177-1_3
关键词:
摘要: This chapter describes a novel methodology for behavior learning of an agent, called Coaching. The proposed method is interactive and iterative which allows human trainer to give subjective evaluation the robotic agent in real time, can update reward function dynamically based on this simultaneously. We demonstrated that capable desired by receiving simple instructions such as positive negative. approach also effective when it difficult determine suitable situation advance. have conducted several experiments with simulated robot arm system, advantage verified throughout those experiments.
springer.com
sci-hub.st 参考文章(14)
David Kurlander, Allen Cypher, Daniel Conrad Halbert, None, Watch what I do: programming by demonstration MIT Press. ,(1993)
Stefan Schaal, Christopher G. Atkeson, Robot Learning From Demonstration international conference on machine learning. pp. 12- 20 ,(1997)
Andrea Lockerd Thomaz, Cynthia Breazeal, Andrew G Barto, Rosalind Picard, Socially guided machine learning Massachusetts Institute of Technology. ,(2006)
Andrea L. Thomaz, Guy Hoffman, Cynthia Breazeal, Experiments in socially guided machine learning: understanding how humans teach human-robot interaction. pp. 359- 360 ,(2006) , 10.1145/1121241.1121315
Tetsunari Inamura, Iwaki Toshima, Hiroaki Tanie, Yoshihiko Nakamura, Embodied Symbol Emergence Based on Mimesis Theory The International Journal of Robotics Research. ,vol. 23, pp. 363- 377 ,(2004) , 10.1177/0278364904042199
Pat Langley, Editorial: On Machine Learning Machine Learning. ,vol. 1, pp. 5- 10 ,(1986) , 10.1023/A:1022687019898
Rainer Ja, Sven R Schmidt-Rohr, Zhixing Xue, Martin Lösch, Rüdiger Dillmann, Learning of probabilistic grasping strategies using Programming by Demonstration international conference on robotics and automation. pp. 873- 880 ,(2010) , 10.1109/ROBOT.2010.5509958
Kenji Doya, Reinforcement Learning in Continuous Time and Space Neural Computation. ,vol. 12, pp. 219- 245 ,(2000) , 10.1162/089976600300015961
C.G. Atkeson, S. Schaal, Learning tasks from a single demonstration international conference on robotics and automation. ,vol. 2, pp. 1706- 1712 ,(1997) , 10.1109/ROBOT.1997.614389
Minija Tamosiunaite, Tamim Asfour, Florentin Wörgötter, Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions Biological Cybernetics. ,vol. 100, pp. 249- 260 ,(2009) , 10.1007/S00422-009-0295-8