Distributional DQN

GPTKB entity

Statements (18)
Predicate Object
gptkbp:instanceOf reinforcement learning algorithm
gptkbp:author Marc G. Bellemare, Will Dabney, Remi Munos
gptkbp:basedOn gptkb:Deep_Q-Network
gptkbp:citation gptkb:ICML
2017
A Distributional Perspective on Reinforcement Learning
gptkbp:distinctFrom standard DQN
gptkbp:hasModel distribution of returns
https://www.w3.org/2000/01/rdf-schema#label Distributional DQN
gptkbp:improves performance on Atari 2600 benchmarks
gptkbp:proposedBy gptkb:Marc_G._Bellemare
gptkb:Will_Dabney
Remi Munos
gptkbp:publicationYear 2017
gptkbp:publishedIn Proceedings of the 34th International Conference on Machine Learning (ICML 2017)
gptkbp:uses categorical distribution
gptkbp:bfsParent gptkb:Rainbow_DQN
gptkbp:bfsLayer 7