A 2-simplicial Transformer, using triple-product attention and tensor-product value updates, outperforms the standard Transformer on a two-key BoxWorld variant in deep reinforcement learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Logic and the $2$-Simplicial Transformer
A 2-simplicial Transformer, using triple-product attention and tensor-product value updates, outperforms the standard Transformer on a two-key BoxWorld variant in deep reinforcement learning.