Reinforcement learning using expectation maximization based guided policy search for stochastic dynamics

Guided policy search algorithms have been proven to work with incredible accuracy not only for controlling complicated dynamical systems, but also in learning optimal policies from exploration of various unseen instances. This paper deals with a trajectory optimization problem for an unknown dynamic...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 484; s. 79 - 88
Hlavní autori: Mallick, Prakash, Chen, Zhiyiong, Zamani, Mohsen
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.05.2022
Predmet:
Expectation maximization
Guided policy search
Maximum likelihood
Reinforcement learning
Stochastic systems
Trajectory optimization
Expectation maximization
Maximum likelihood
Stochastic systems
Guided policy search
Trajectory optimization
Reinforcement learning
ISSN:0925-2312, 1872-8286
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Guided policy search algorithms have been proven to work with incredible accuracy not only for controlling complicated dynamical systems, but also in learning optimal policies from exploration of various unseen instances. This paper deals with a trajectory optimization problem for an unknown dynamical system subject to measurement noise using expectation maximization and extends it to learning (optimal) policies which have less stochasticity in trajectories because of the higher exploitation efficiency. Theoretical and empirical evidence of learned optimal policies for the new approach is depicted in comparison to some well known baselines which are evaluated on an autonomous system with widely used performance metrics.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.01.142