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...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 484; pp. 79 - 88
Main Authors: Mallick, Prakash, Chen, Zhiyiong, Zamani, Mohsen
Format: Journal Article
Language:English
Published: Elsevier B.V 01.05.2022
Subjects:
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
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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