REValueD: 分解可能なマルコフ決定過程のための正則化アンサンブル価値分解
REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
高次元離散行動空間での強化学習において、価値分解の過大評価バイアスとターゲット分散の増大をアンサンブルと正則化損失で解決する手法を提案し、DeepMind Control Suiteで有効性を示した。
著者: David Ireland, Giovanni Montana
分類: cs.LG, cs.AI
原文アブストラクト
Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent reinforcement learning, to tackle this challenge. This study delves deep into the effects of this value-decomposition, revealing that whilst it curtails the over-estimation bias inherent to Q-learning algorithms, it amplifies target variance. To counteract this, we present an ensemble of critics to mitigate target variance. Moreover, we introduce a regularisation loss that helps to mitigate the effects that exploratory actions in one dimension can have on the value of optimal actions in other dimensions. Our novel algorithm, REValueD, tested on discretised versions of the DeepMind Control Suite tasks, showcases superior performance, especially in the challenging humanoid and dog tasks. We further dissect the factors influencing REValueD's performance, evaluating the significance of the regularisation loss and the scalability of REValueD with increasing sub-actions per dimension.
