This chapter entertains the idea of deriving filtering algorithms using (deep) reinforcement learning methods. After covering the basics of reinforcement learning, it is shown that both variational inference and reinforcement learning can be viewed as instances of a generic expectation maximization problem. The equivalence between variational inference and reinforcement learning allows for developing novel filtering algorithms. The reviewed application is the battery state‐of‐charge estimation.
Reinforcement Learning‐Based Filter
Nonlinear Filters ; 203-211
12.04.2022
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Traffic light control method based on deep reinforcement learning and inverse reinforcement learning
Europäisches Patentamt | 2023
|A State Space Filter for Reinforcement Learning in Partially Observable Markov Decision Processes
British Library Online Contents | 2009
|