深層強化学習における流動的適応性へ：生物系の知見に学ぶ適応的柔軟性
From Crystallized Adaptivity to Fluid Adaptivity in Deep Reinforcement Learning -- Insights from Biological Systems on Adaptive Flexibility
生物の「流動的適応性」を参考に、深層強化学習が環境変化に柔軟に対応できない課題を分析し、将来のAIにその能力を持たせるための研究戦略を論じた論文。
著者: Malte Schilling, Helge Ritter, Frank W. Ohl
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures are combined with incremental learning schemes for sequential tasks that include interaction-based, but often delayed feedback. Despite their impressive successes, modern machine-learning approaches, including deep reinforcement learning, still perform weakly when compared to flexibly adaptive biological systems in certain naturally occurring scenarios. Such scenarios include transfers to environments different than the ones in which the training took place or environments that dynamically change, both of which are often mastered by biological systems through a capability that we here term "fluid adaptivity" to contrast it from the much slower adaptivity ("crystallized adaptivity") of the prior learning from which the behavior emerged. In this article, we derive and discuss research strategies, based on analyzes of fluid adaptivity in biological systems and its neuronal modeling, that might aid in equipping future artificially intelligent systems with capabilities of fluid adaptivity more similar to those seen in some biologically intelligent systems. A key component of this research strategy is the dynamization of the problem space itself and the implementation of this dynamization by suitably designed flexibly interacting modules.
