AIApr 26, 2017
The MacGyver Test - A Framework for Evaluating Machine Resourcefulness and Creative Problem Solving
arXiv:1704.08350v13 citations
Originality Incremental advance
AI Analysis
This addresses the need for practical evaluation methods for AI problem-solving, though it appears incremental as it builds on existing notions of testing.
The paper tackles the problem of evaluating machine intelligence in open worlds by proposing the MacGyver Test framework, which assesses resilience and resourcefulness of artificial agents.
Current measures of machine intelligence are either difficult to evaluate or lack the ability to test a robot's problem-solving capacity in open worlds. We propose a novel evaluation framework based on the formal notion of MacGyver Test which provides a practical way for assessing the resilience and resourcefulness of artificial agents.