Logic and the $2$-Simplicial Transformer
This addresses logical reasoning challenges in deep reinforcement learning, but appears incremental as it builds on existing Transformer architectures.
The paper tackled the problem of logical reasoning in deep reinforcement learning by introducing the $2$-simplicial Transformer, which extends the Transformer with higher-dimensional attention and tensor products, showing it serves as a useful inductive bias.
We introduce the $2$-simplicial Transformer, an extension of the Transformer which includes a form of higher-dimensional attention generalising the dot-product attention, and uses this attention to update entity representations with tensor products of value vectors. We show that this architecture is a useful inductive bias for logical reasoning in the context of deep reinforcement learning.