M.: Interactive policy learning through confidence-based autonomy

M.: Interactive policy learning through confidence-based autonomy (2009)

Cached

Download Links

by Sonia Chernova , Manuela Veloso

Venue:	J. Artificial Intelligence Research
Citations:	35 - 10 self

BibTeX

@ARTICLE{Chernova09m.:interactive,
    author = {Sonia Chernova and Manuela Veloso},
    title = {M.: Interactive policy learning through confidence-based autonomy},
    journal = {J. Artificial Intelligence Research},
    year = {2009},
    pages = {1--25}
}

Bookmark

OpenURL

Abstract

We present Confidence-Based Autonomy (CBA), an interactive algorithm for policy learning from demonstration. The CBA algorithm consists of two components which take advantage of the complementary abilities of humans and computer agents. The first component, Confident Execution, enables the agent to identify states in which demonstration is required, to request a demonstration from the human teacher and to learn a policy based on the acquired data. The algorithm selects demonstrations based on a measure of action selection confidence, and our results show that using Confident Execution the agent requires fewer demonstrations to learn the policy than when demonstrations are selected by a human teacher. The second algorithmic component, Corrective Demonstration, enables the teacher to correct any mistakes made by the agent through additional demonstrations in order to improve the policy and future task performance. CBA and its individual components are compared and evaluated in a complex simulated driving domain. The complete CBA algorithm results in the best overall learning performance, successfully reproducing the behavior of the teacher while balancing the tradeoff between number of demonstrations and number of incorrect actions during learning. 1.

Citations

2827	Reinforcement Learning: An Introduction - Sutton, Barto - 1998
340	Selection of relevant features and examples in machine learning - Blum, Langley - 1997
334	Improving generalization with active learning - Cohn, Atlas, et al. - 1994
248	S.: Robot learning from demonstration - Atkeson, Schaal - 1997
143	Apprenticeship learning via inverse reinforcement learning - Abbeel, Ng - 2004
41	Teaching robots by moulding behavior and scaffolding the environment - Nehaniv, L, et al. - 2004
38	C.: Tutelage and socially guided robot learning - Lockerd, Breazeal - 2004
36	C.: Accelerating reinforcement learning through implicit imitation - Price, Boutilier - 2003
27	M.: Confidence-based policy learning from demonstration using Gaussian mixture models - Chernova, Veloso
26	B.: A survey of robot learning from demonstration. Robotics and Autonomous Systems (2008 - Argall, Chernova, et al.
23	Making Reinforcement Learning Work on Real Robots - Smart - 2002
20	Acquisition of probabilistic behavior decision model based on the interactive teaching method - Inamura, Inaba, et al. - 1999
19	M.: Learning equivalent action choices from demonstration - Chernova, Veloso - 2008
16	Learning to act from observation and practice - Bentivegna, Atkeson, et al.
16	On integrating apprentice learning and reinforcement learning,” Electronic Doctoral Dissertations for UMass Amherst - Clouse - 1996
15	Skill acquisition and use for a dynamically-balancing soccer robot - Browning, Xu, et al.
15	A framework for learning from demonstration, generalization and practice in human-robot domains - Nicolescu
15	Knowledge transfer using local features - Stolle, Atkeson - 2007
11	M (2007) Learning from demonstration with the critique of a human teacher - Argall, Browning, et al.
10	M.: Teaching collaborative multi-robot tasks through demonstration - Chernova, Veloso - 2008
5	Integrating advice with reinforcement learning - Papudesi - 2002
2	A hierarchical multi-module learning system based on self-interpretation of instructions by coach - Takahashi, Hikita, et al. - 2004
1	24 Policy Learning through Confidence-Based Autonomy - Grollman, Jenkins - 2007