DataSheet1_Towards the Neuroevolution of Low-level artificial general intelligence.PDF

In this work, we argue that the search for Artificial General Intelligence should start from a much lower level than human-level intelligence. The circumstances of intelligent behavior in nature resulted from an organism interacting with its surrounding environment, which could change over time and exert pressure on the organism to allow for learning of new behaviors or environment models. Our hypothesis is that learning occurs through interpreting sensory feedback when an agent acts in an environment. For that to happen, a body and a reactive environment are needed. We evaluate a method to evolve a biologically-inspired artificial neural network that learns from environment reactions named Neuroevolution of Artificial General Intelligence, a framework for low-level artificial general intelligence. This method allows the evolutionary complexification of a randomly-initialized spiking neural network with adaptive synapses, which controls agents instantiated in mutable environments. Such a configuration allows us to benchmark the adaptivity and generality of the controllers. The chosen tasks in the mutable environments are food foraging, emulation of logic gates, and cart-pole balancing. The three tasks are successfully solved with rather small network topologies and therefore it opens up the possibility of experimenting with more complex tasks and scenarios where curriculum learning is beneficial.

本研究认为，通用人工智能（Artificial General Intelligence，AGI）的探索应当从远低于人类智能水平的层级起步。自然界中智能行为的产生，源于生物体与其周遭环境的交互：环境会随时间动态变化，并对生物体施加选择压力，使其得以学习新的行为模式或环境模型。我们的核心假设为：当AI智能体（AI Agent）在环境中行动时，学习过程通过解读感官反馈得以实现。要达成这一目标，需要具备实体躯体与具备反应性的环境。我们对一种受生物学启发的人工神经网络训练方法进行了评估，该方法可从环境反馈中学习，名为通用人工智能神经进化（Neuroevolution of Artificial General Intelligence），是一种面向低层级通用人工智能的研究框架。此方法可实现带有自适应突触的随机初始化脉冲神经网络（spiking neural network）的进化式复杂化，该网络可控制部署于动态可变环境中的智能体。借助此配置，我们可对控制器的适应性与通用性开展基准测试。我们在动态可变环境中选取的测试任务包括食物觅食、逻辑门仿真以及小车立杆平衡（cart-pole balancing）。上述三项任务均可通过规模相对较小的网络拓扑结构成功求解，这为开展更复杂的、适合课程学习（curriculum learning）的任务与场景实验提供了可能。