Research Area:  Machine Learning

Abstract:

Recent aerospace systems increasingly demand model-free controller synthesis, and autonomous operations require adaptability to uncertainties in partially observable environments. This paper applies distributional reinforcement learning to synthesize risk-sensitive, robust model-free policies for aerospace control. We investigate the use of distributional soft actor-critic (DSAC) agents for flight control and compare their learning characteristics and tracking performance with the soft actor-critic (SAC) algorithm. The results show that (1) the addition of distributional critics significantly improves learning consistency, (2) risk-averse agents increase flight safety by avoiding uncertainties in the environment.

Keywords:  

Author(s) Name:  Peter Seres, Cheng Liu, Erik-Jan van Kampen

Publisher name:  ScienceDirect

DOI:  10.1016/j.ifacol.2023.10.1097

Volume Information:  Volume 56, (2023)

Paper Link:   https://www.sciencedirect.com/science/article/pii/S2405896323015008