Improving the Performance of Batch-Constrained Reinforcement Learning in Continuous Action Domains via Generative Adversarial Networks

The Batch-Constrained Q-learning algorithm is shown to overcome the extrapolation error and enable deep reinforcement learning agents to learn from a previously collected fixed batch of transitions. However, due to conditional Variational Autoencoders (VAE) used in the data generation module, the BC...

Full description

Bibliographic Details

Published in:	2022 30th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors:	Saglam, Baturay, Dalmaz, Onat, Gonc, Kaan, Kozat, Suleyman S.
Format:	Conference Proceeding
Language:	English Turkish
Published:	IEEE 15.05.2022
Subjects:	Aerospace electronics batch-constrained reinforcement learning Deep learning deep reinforcement learning Employment Extrapolation offline re-inforcement learning Q-learning Signal processing Signal processing algorithms
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!