Print Email Facebook Twitter Distributional Reinforcement Learning for Flight Control Title Distributional Reinforcement Learning for Flight Control: A risk-sensitive approach to aircraft attitude control using Distributional RL Author Seres, Peter (TU Delft Aerospace Engineering; TU Delft Control & Simulation) Contributor van Kampen, E. (mentor) Liu, C. (mentor) Degree granting institution Delft University of Technology Programme Aerospace Engineering Date 2022-11-09 Abstract With the recent increase in the complexity of aerospace systems and autonomous operations, there is a need for an increased level of adaptability and model-free controller synthesis. Such operations require the controller to maintain safety and performance without human intervention in non-static environments with partial observability and uncertainty. Deep Reinforcement Learning (DRL) algorithms have the potential to increase the safety and autonomy of aerospace control systems. It has been shown that the soft actor-critic (SAC) algorithm can achieve robust control of a CS-25 certified aircraft and has the generalization power to react to failure scenarios. Traditional DRL approaches, such as the state-of-the-art SAC algorithm struggle with inconsistent learning in high-dimensional tasks and fall short of modelling uncertainty and risk in the environment. In contrast, distributional RL algorithms estimate the entire probability distribution of rewards, improve the learning characteristics and enable the synthesis of risk- sensitive policies. This paper demonstrates the improved learning characteristics of distributional soft actor-critic (DSAC) compared to traditional SAC and discusses the benefits of risk-sensitive learning applied to flight control. We show that the addition of distributional critics significantly improves learning consistency, and successfully approximates the uncertainty when applied to a fully-coupled attitude control task of a jet aircraft. Subject Reinforcement Learning (RL)Deep Reinforcement LearningDistributional Reinforcement LearningFlight ControlAutonomous Control To reference this document use: http://resolver.tudelft.nl/uuid:6cd3efd1-b755-4b04-8b9b-93f9dabb6108 Bibliographical note Public code repository https://github.com/peter-seres/dsac-flight Part of collection Student theses Document type master thesis Rights © 2022 Peter Seres Files PDF Msc_Thesis_Report_Peter_Seres.pdf 12.77 MB Close viewer /islandora/object/uuid:6cd3efd1-b755-4b04-8b9b-93f9dabb6108/datastream/OBJ/view