Social-Task Learning for HRI

In this paper, we introduce a novel method for learning simultaneously a task and the related social interaction. We present an architecture based on Learning Classifier Systems that simultaneously learns a model of social interaction and uses it to bootstrap task learning, while minimizing the number of interactions with the human. We validate our method in simulation and we prove the feasibility of our approach on a real robot.

[1]  Pierre-Yves Oudeyer,et al.  Robot learning simultaneously a task and how to interpret human instructions , 2013, 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[2]  Eduardo F. Morales,et al.  Dynamic Reward Shaping: Training a Robot by Voice , 2010, IBERAMIA.

[3]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[4]  Sonia Chernova,et al.  Effect of human guidance and state space size on Interactive Reinforcement Learning , 2011, 2011 RO-MAN.

[5]  Peter Stone,et al.  Combining manual feedback with subsequent MDP reward signals for reinforcement learning , 2010, AAMAS.

[6]  Andrea Lockerd Thomaz,et al.  Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance , 2006, AAAI.

[7]  Farbod Fahimi,et al.  Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning , 2011, 2011 IEEE International Conference on Rehabilitation Robotics.

[8]  Christopher E. Peters,et al.  Social-Task Engagement : Striking a Balance between the Robot and the Task , 2013 .

[9]  B. Scassellati,et al.  Learning to refine behavior using prosodic feedback , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[10]  Mohamed Chetouani,et al.  Socially Guided XCS: Using Teaching Signals to Boost Learning , 2015, GECCO.

[11]  Peter Stone,et al.  A social reinforcement learning agent , 2001, AGENTS '01.

[12]  Stewart W. Wilson,et al.  Noname manuscript No. (will be inserted by the editor) Learning Classifier Systems: A Survey , 2022 .