Adaptive Rational Activations to Boost Deep Reinforcement Learning

arXiv:2102.09407v4 Announce Type: replace
Abstract: Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility than previously anticipated. This perspective should be critical in the context of constantly changing distinct reinforcement learning environments, yet current approaches still primarily employ static activation functions. In this work, we motivate why rationals are suitable for adaptable activation functions and why their inclusion into neural networks is crucial. Inspired by recurrence …

abstract arxiv biology boost computational context cs.lg current environments individual neurons insights intelligence neurons perspective reinforcement reinforcement learning responsibility show type