Center for Advanced Intelligence Project

Title:
The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

Abstract:
In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture. Such systems have inspired development of artificial intelligence algorithms in areas such as swarm optimization and cellular automata. Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed each sensory input from the environment into distinct, but identical neural networks, each with no fixed relationship with one another. We show that these sensory networks can be trained to integrate information received locally, and through communication via an attention mechanism, can collectively produce a globally coherent policy. Moreover, 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 that are broadly applicable. Interactive demo and videos of our results: https://attentionneuron.github.io/

Bio:
David Ha is a Research Scientist at Google Brain. His research is closely inspired by biological intelligent systems. He has made several significant contributions to the field of deep reinforcement learning such as his “World Models” paper since joining Google in 2016. Prior to that – with a background in finance – he worked at Goldman Sachs as a Managing Director where he co-ran the fixed-income trading business in Japan.
https://scholar.google.com/citations?user=J1j92GsxVUMC&hl=en