Salvato in:
Dettagli Bibliografici
Autori principali: Bhatt, Aditya, Palenicek, Daniel, Belousov, Boris, Argus, Max, Amiranashvili, Artemij, Brox, Thomas, Peters, Jan
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:https://arxiv.org/abs/1902.05605
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909148252209152
author Bhatt, Aditya
Palenicek, Daniel
Belousov, Boris
Argus, Max
Amiranashvili, Artemij
Brox, Thomas
Peters, Jan
author_facet Bhatt, Aditya
Palenicek, Daniel
Belousov, Boris
Argus, Max
Amiranashvili, Artemij
Brox, Thomas
Peters, Jan
contents Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while maintaining a low UTD ratio of 1. Notably, CrossQ does not rely on advanced bias-reduction schemes used in current methods. CrossQ's contributions are threefold: (1) it matches or surpasses current state-of-the-art methods in terms of sample efficiency, (2) it substantially reduces the computational cost compared to REDQ and DroQ, (3) it is easy to implement, requiring just a few lines of code on top of SAC.
format Preprint
id arxiv_https___arxiv_org_abs_1902_05605
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Bhatt, Aditya
Palenicek, Daniel
Belousov, Boris
Argus, Max
Amiranashvili, Artemij
Brox, Thomas
Peters, Jan
Machine Learning
Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while maintaining a low UTD ratio of 1. Notably, CrossQ does not rely on advanced bias-reduction schemes used in current methods. CrossQ's contributions are threefold: (1) it matches or surpasses current state-of-the-art methods in terms of sample efficiency, (2) it substantially reduces the computational cost compared to REDQ and DroQ, (3) it is easy to implement, requiring just a few lines of code on top of SAC.
title CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
topic Machine Learning
url https://arxiv.org/abs/1902.05605