Combining system identification with reinforcement learning-based MPC
Peer reviewed, Journal article
Published version
Åpne
Permanent lenke
https://hdl.handle.net/11250/2775033Utgivelsesdato
2020Metadata
Vis full innførselSamlinger
Originalversjon
http://dx.doi.org/10.1016/j.ifacol.2020.12.2294Sammendrag
In this paper we propose and compare methods for combining system identification (SYSID) and reinforcement learning (RL) in the context of data-driven model predictive control (MPC). Assuming a known model structure of the controlled system, and considering a parametric MPC, the proposed approach simultaneously: a) Learns the parameters of the MPC using RL in order to optimize performance, and b) fits the observed model behaviour using SYSID. Six methods that avoid conflicts between the two optimization objectives are proposed and evaluated using a simple linear system. Based on the simulation results, hierarchical, parallel projection, nullspace projection, and singular value projection achieved the best performance.