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.
翻译:生物学的最新洞察显示,智能不仅来自神经元之间的联系,而且个别神经元承担的计算责任也比以前预期的要多。在不断变化的不同强化学习环境中,这一视角至关重要,但目前的做法仍然主要使用静态激活功能。在这项工作中,我们提出为什么理性适合适应激活功能,为什么将其纳入神经网络至关重要。由于残余网络的重复出现,我们得出了一个条件,即理性单位在剩余连接下关闭,并形成一个自然的常规版本:即经常标准。我们证明,为流行算法配备(经常)逻辑激活功能可以持续改善阿塔里游戏,特别是将简单的DQN转化为一种坚实的方法,对DQN和彩虹具有竞争力。