De Lellis, Francesco; Coraggio, Marco; Russo, Giovanni; Musolesi, Mirco; Di Bernardo, Mario; (2022) Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control. In: Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel, (eds.) Proceedings of The 4th Annual Learning for Dynamics and Control Conference. (pp. pp. 1048-1059). MIT Press: Stanford, CA, USA.

Preview

Text Musolesi_L4DC_22.pdf - Accepted Version Download (1MB) | Preview

Abstract

We present an architecture where a feedback controller derived on an approximate model of the environment assists the learning process to enhance its data efficiency. This architecture, which we term as Control-Tutored Q-learning (CTQL), is presented in two alternative flavours. The former is based on defining the reward function so that a Boolean condition can be used to determine when the control tutor policy is adopted, while the latter, termed as probabilistic CTQL (pCTQL), is instead based on executing calls to the tutor with a certain probability during learning. Both approaches are validated, and thoroughly benchmarked against Q-Learning, by considering the stabilization of an inverted pendulum as defined in OpenAI Gym as a representative problem.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item