General AI Challenge - Round One: Gradual Learning

Abstract

The General AI Challenge is an initiative to encourage the wider artificial intelligence community to focus on important problems in building intelligent machines with more general scope than is currently possible. The challenge comprises of multiple rounds, with the first round focusing on gradual learning, i.e. the ability to re-use already learned knowledge for efficiently learning to solve subsequent problems. In this article, we will present details of the first round of the challenge, its inspiration and aims. We also outline a more formal description of the challenge and present a preliminary analysis of its curriculum, based on ideas from computational mechanics. We believe, that such formalism will allow for a more principled approach towards investigating tasks in the challenge, building new curricula and for potentially improving consequent challenge rounds.

Presented as keynote talk at IJCAI Workshop on Evaluating General-Purpose AI (EGPAI 2017)

References in corpus (6)

• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Learning to reinforcement learn
• Deep vs. shallow networks : An approximation theory perspective
• A Framework for Searching for General Artificial Intelligence
• CommAI: Evaluating the first steps towards a useful general AI
• Micro-Objective Learning : Accelerating Deep Reinforcement Learning through the Discovery of Continuous Subgoals