Towards the Neuroevolution of Low-level Artificial General Intelligence
Oslo Metropolitan University(奥斯陆城市大学);Norwegian University of Science and Technology(挪威科技大学);University of Oslo(奥斯陆大学);Simula Metropolitan Centre for Digital Engineering(Simula大都会数字工程中心);Østfold University College(东福尔大学学院)
Sidney Pontes-Filho, Kristoffer Olsen, Anis Yazidi, Michael A. Riegler, Pål Halvorsen, Stefano Nichele
In this work, we argue that the search for Artificial General Intelligence (AGI) 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 (NAGI), a framework for low-level AGI. 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.
An Efficient Application of Neuroevolution for Competitive Multiagent Learning
Vellore Institute of Technology(韦洛尔理工学院)
多智能体系统为使用强化学习算法评估和分析现实世界的问题提供了一个理想的环境。大多数传统的多智能体学习方法都受到长训练周期和高计算复杂性的影响。NEAT(NeuroEvolution of Augmenting Topologies)是一种流行的进化策略,用于获得最佳性能的神经网络架构,通常用于解决人工智能领域的优化问题。本文利用NEAT算法实现竞争性多智能体学习的修改乒乓游戏环境中的有效方式。竞争主体遵守不同的规则,但具有相似的观测空间参数。该算法利用环境的这一属性来定义一个奇异的神经进化过程,获得所有代理的最优策略。编译的结果表明,所提出的实现在一个非常短的训练期内达到理想的行为相比,现有的多智能体强化学习模型。
Artificial Intelligence : from Research to Application ; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019)
TriRhenaTech联盟大学及其合作伙伴在2019年3月13日在奥芬堡举行的三国会议“人工智能:从研究到应用”上展示了他们在人工智能领域的能力以及与行业的跨境合作。TriRhenaTech联盟是上莱茵河三国大都市区的大学网络,包括位于富特旺根、凯泽斯滕、卡尔斯鲁厄和奥芬堡的德国应用科学大学,巴登-符腾堡州合作州立大学Loerrach,法国大学网络阿尔萨斯理工大学,瑞士国立大学(由14所工程、建筑和管理领域的“高等院校”组成)和瑞士西北应用科学与艺术大学(University of Applied Sciences and Arts Northwestern Switzerland)。该联盟的共同目标是加强知识、研究和技术的转移,以及学生的跨境流动。
Watershed of Artificial Intelligence: Human Intelligence, Machine Intelligence, and Biological Intelligence
University of Brasilia(巴西利亚大学);University of Sao Paulo(圣保罗大学)
本文回顾了23年前提出的“一次学习”机制,以及随后在图像分类中的“一次性学习”和在客观检测中的“You Only Look Once - YOLO”的成功。分析了人工智能(AI)的发展现状,提出AI应明确划分为人工人类智能(AHI)、人工机器智能(AMI)和人工生物智能(ABI),这也将是AI理论和应用发展的主要方向。作为人工智能分支的分水岭,讨论了一些分类标准和方法:1)面向人类、面向机器和面向生物的人工智能研发; 2)通过模糊度上升或模糊度下降处理的信息输入; 3)使用一个/几个或大样本进行知识学习。