モデルベース事前分布を活用したモデルフリー強化学習
MBMF: Model-Based Priors for Model-Free Reinforcement Learning
確率的ダイナミクスモデルを学習し、それをモデルフリー最適化の事前分布として組み込むことで、データ効率とコスト効率を両立させる強化学習手法を提案した。
著者: Somil Bansal, Roberto Calandra, Kurtland Chua, Sergey Levine, Claire Tomlin
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to real world domains that are appropriate to its corresponding strengths. In this paper, we present a new approach aimed at bridging the gap between these two paradigms. We aim to take the best of the two paradigms and combine them in an approach that is at the same time data-efficient and cost-savvy. We do so by learning a probabilistic dynamics model and leveraging it as a prior for the intertwined model-free optimization. As a result, our approach can exploit the generality and structure of the dynamics model, but is also capable of ignoring its inevitable inaccuracies, by directly incorporating the evidence provided by the direct observation of the cost. Preliminary results demonstrate that our approach outperforms purely model-based and model-free approaches, as well as the approach of simply switching from a model-based to a model-free setting.
