Interactive policy learning through confidence-based autonomy
作者： S. Chernova , M. Veloso
DOI: 10.1613/JAIR.2584
关键词:
摘要: We present Confidence-Based Autonomy (CBA), an interactive algorithm for policy learning from demonstration. The CBA consists of two components which take advantage the complimentary abilities humans and computer agents. first component, Confident Execution, enables agent to identify states in demonstration is required, request a human teacher learn based on acquired data. selects demonstrations measure action selection confidence, our results show that using Execution requires fewer than when are selected by teacher. second algorithmic Corrective Demonstration, correct any mistakes made through additional order improve future task performance. its individual compared evaluated complex simulated driving domain. complete best overall performance, successfully reproducing behavior while balancing tradeoff between number incorrect actions during learning.
arxiv.org
sci-hub.st 参考文章(24)
Cynthia Breazeal, Andrea L. Thomaz, Reinforcement learning with human teachers: evidence of feedback and guidance with implications for learning performance national conference on artificial intelligence. pp. 1000- 1005 ,(2006)
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Stefan Schaal, Christopher G. Atkeson, Robot Learning From Demonstration international conference on machine learning. pp. 12- 20 ,(1997)
Paul E. Utgoff, Jeffery Allen Clouse, On integrating apprentice learning and reinforcement learning University of Massachusetts Amherst. ,(1996)
Yasutake Takahashi, Koichi Hikita, Minoru Asada, A Hierarchical Multi-module Learning System Based on Self-interpretation of Instructions by Coach robot soccer world cup. pp. 576- 583 ,(2003) , 10.1007/978-3-540-25940-4_54
DARRIN C. BENTIVEGNA, CHRISTOPHER G. ATKESON, ALEŠ UDE, GORDON CHENG, LEARNING TO ACT FROM OBSERVATION AND PRACTICE International Journal of Humanoid Robotics. ,vol. 01, pp. 585- 611 ,(2004) , 10.1142/S0219843604000307
Sonia Chernova, Manuela Veloso, Confidence-based policy learning from demonstration using Gaussian mixture models adaptive agents and multi-agents systems. pp. 233- ,(2007) , 10.1145/1329125.1329407
Brenna D. Argall, Sonia Chernova, Manuela Veloso, Brett Browning, A survey of robot learning from demonstration Robotics and Autonomous Systems. ,vol. 57, pp. 469- 483 ,(2009) , 10.1016/J.ROBOT.2008.10.024
Pieter Abbeel, Andrew Y. Ng, Apprenticeship learning via inverse reinforcement learning Twenty-first international conference on Machine learning - ICML '04. pp. 1- 8 ,(2004) , 10.1145/1015330.1015430
Avrim L. Blum, Pat Langley, Selection of relevant features and examples in machine learning Artificial Intelligence. ,vol. 97, pp. 245- 271 ,(1997) , 10.1016/S0004-3702(97)00063-5