カスケード属性ネットワーク：階層型ニューラルネットによる強化学習制御方策の分解
Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks
制御タスクの要求制約（属性）ごとに方策を階層的に分解するカスケード属性ネットワークを提案し、複数属性のタスクでもモジュールを組み合わせるだけでゼロショットに制御方策を得られることをロボット制御2例で示した。
著者: Haonan Chang, Zhuo Xu, Masayoshi Tomizuka
分類: cs.RO
原文アブストラクト
Reinforcement learning methods have been developed to achieve great success in training control policies in various automation tasks. However, a main challenge of the wider application of reinforcement learning in practical automation is that the training process is hard and the pretrained policy networks are hardly reusable in other similar cases. To address this problem, we propose the cascade attribute network (CAN), which utilizes its hierarchical structure to decompose a complicated control policy in terms of the requirement constraints, which we call attributes, encoded in the control tasks. We validated the effectiveness of our proposed method on two robot control scenarios with various add-on attributes. For some control tasks with more than one add-on attribute attribute, by directly assembling the attribute modules in cascade, the CAN can provide ideal control policies in a zero-shot manner.
