Toward supervised reinforcement learning with partial states for social HRI

Senft, Emmanuel, Lemaignan, Severin, Baxter, Paul and Belpaeme, Tony (2017) Toward supervised reinforcement learning with partial states for social HRI. In: 4th AAAI FSS on Artificial Intelligence for Social Human-Robot Interaction (AI-HRI), 9 - 11 November 2017, Arlington, Virginia.

Full content URL:

17 AI-HRI Emmanuel.pdf
17 AI-HRI Emmanuel.pdf - Whole Document

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


Social interacting is a complex task for which machine learning holds particular promise. However, as no sufficiently accurate simulator of human interactions exists today, the learning of social interaction strategies has to happen online in the real world. Actions executed by the robot impact on humans, and as such have to be carefully selected, making it impossible to rely on random exploration. Additionally, no clear reward function exists for social interactions. This implies that traditional approaches used for Reinforcement Learning cannot be directly applied for learning how to interact with the social world. As such we argue that robots will profit from human expertise and guidance to learn social interactions. However, as the quantity of input a human can provide is limited, new methods have to be designed to use human input more efficiently. In this paper we describe a setup in which we combine a framework called Supervised Progressively Autonomous Robot Competencies (SPARC), which allows safer online learning with Reinforcement Learning, with the use of partial states rather than full states to accelerate generalisation and obtain a usable action policy more quickly.

Keywords:social interaction, machine learning, human-robot interaction, SPARC
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:30193
Deposited On:02 Feb 2018 12:03

Repository Staff Only: item control page