DrQ

GPTKB entity

Statements (23)
Predicate Object
gptkbp:instanceOf reinforcement learning algorithm
gptkbp:appliesTo continuous control tasks
gptkbp:author Agrawal, Abhishek
Dhariwal, Prafulla
Funk, Jonathan
Kostrikov, Denis
Kumar, Aviral
Todorov, Emanuel
Yarats, Denis
gptkbp:citation Reinforcement Learning with Augmented Data
gptkbp:developedBy gptkb:DeepMind
gptkbp:fullName Data-regularized Q
https://www.w3.org/2000/01/rdf-schema#label DrQ
gptkbp:improves sample efficiency
SAC on some benchmarks
gptkbp:introducedIn 2020
gptkbp:openSource https://github.com/denisyarats/drq
gptkbp:publishedIn gptkb:arXiv
gptkbp:relatedTo gptkb:Soft_Actor-Critic
Deep Q-Learning
gptkbp:uses data augmentation
gptkbp:bfsParent gptkb:Denis_Yarats
gptkbp:bfsLayer 7