A Survey on Interactive Reinforcement Learning
Authors:
Open Access
- 3 July 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1195-1209
Abstract
Interactive reinforcement learning (RL) has been successfully used in various applications in different fields, which has also motivated HCI researchers to contribute in this area. In this paper, we survey interactive RL to empower human-computer interaction (HCI) researchers with the technical background in RL needed to design new interaction techniques and propose new applications. We elucidate the roles played by HCI researchers in interactive RL, identifying ideas and promising research directions. Furthermore, we propose generic design principles that will provide researchers with a guide to effectively implement interactive RL applications.Keywords
This publication has 47 references indexed in Scilit:
- Robots learn to dance through interaction with humansNeural Computing and Applications, 2013
- Heuristically-Accelerated Multiagent Reinforcement LearningIEEE Transactions on Cybernetics, 2013
- Training a Robot via Human Feedback: A Case Study2013
- A survey of inverse reinforcement learning techniquesInternational Journal of Intelligent Computing and Cybernetics, 2012
- How Humans Teach AgentsInternational Journal of Social Robotics, 2012
- Towards Understanding How Humans Teach Robots2011
- Natural actor–critic algorithmsAutomatica, 2009
- Teachable robots: Understanding human teaching behavior to build more effective robot learnersArtificial Intelligence, 2008
- Cobot in LambdaMOO: An Adaptive Social Statistics AgentAutonomous Agents and Multi-Agent Systems, 2006
- Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 1992