https://arxiv.org/abs/2109.02869v1
The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning
Yujin Tang, David Ha
“…we build systems that feed each sensory input from the environment into distinct, but identical neural networks…. the system can still perform its task even if the ordering of its inputs is randomly permuted several times during an episode. These permutation invariant systems also display useful robustness and generalization properties…”