Back to Search Start Over

Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse

Authors :
Queeney, James
Paschalidis, Ioannis Ch.
Cassandras, Christos G.
Publication Year :
2022

Abstract

We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the efficiency of sample reuse, addressing a trade-off between two important deployment requirements for real-world control: (i) practical performance guarantees and (ii) data efficiency. We demonstrate the benefits of this new class of algorithms through extensive experimental analysis on a broad range of simulated control tasks.<br />Comment: Accepted for publication in IEEE Transactions on Automatic Control

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2206.13714
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/TAC.2024.3454011