成長するQネットワーク：適応的制御解像度による連続制御タスクの解決
Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution
離散行動空間を粗い解像度から細かい解像度へと成長させることで、連続制御タスクにおける強化学習の性能を向上させる手法を提案。
著者: Tim Seyde, Peter Werner, Wilko Schwarting, Markus Wulfmeier, Daniela Rus
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration characteristics while final performance does not visibly suffer in the absence of action penalization in line with optimal control theory. In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency, but action costs can be detrimental to exploration during early training. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution, taking advantage of recent results in decoupled Q-learning to scale our approach to high-dimensional action spaces up to dim(A) = 38. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
