The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors

Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require an exponentially increasing number of samples, their development is restricted to...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-01
Hauptverfasser:	Guss, William H, Codel, Cayden, Hofmann, Katja, Houghton, Brandon, Kuno, Noboru, Milani, Stephanie, Mohanty, Sharada, Diego Perez Liebana, Salakhutdinov, Ruslan, Topin, Nicholay, Veloso, Manuela, Wang, Phillip
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Competition Computer simulation Control methods Datasets Decision making Domains Machine learning Sampling methods
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!