Adaptive Rational Activations to Boost Deep Reinforcement Learning
This work addresses the need for more adaptable neural networks in reinforcement learning, offering a domain-specific improvement for AI agents in dynamic environments.
The paper tackled the problem of static activation functions in deep reinforcement learning by introducing adaptive rational activations, demonstrating consistent improvements on Atari games, with simple DQN becoming competitive to DDQN and Rainbow.
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 in residual networks, we derive a condition under which rational units are closed under residual connections and formulate a naturally regularised version: the recurrent-rational. We demonstrate that equipping popular algorithms with (recurrent-)rational activations leads to consistent improvements on Atari games, especially turning simple DQN into a solid approach, competitive to DDQN and Rainbow.