315 citations · 346 across the 2 of their papers we have counts for
2 papers
cs.LG2019★ 31 cited
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
Lasse Espeholt, Raphaël Marinier, Piotr Stanczyk +2
We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possi…
cs.CL2016★ 315 cited
Neural Machine Translation in Linear Time
Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan +3
We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source se…