非対称アーキテクチャによる深層強化学習エージェントの展開時推論コスト削減
Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture
高コストな方策と低コストな方策を切り替える非対称アーキテクチャを提案し、ロボット制御ベンチマークで性能を保ちつつ推論コストを削減した。
著者: Chin-Jui Chang, Yu-Wei Chu, Chao-Hsien Ting, Hao-Kang Liu, Zhang-Wei Hong, Chun-Yi Lee
分類: cs.AI, cs.RO
原文アブストラクト
Deep reinforcement learning (DRL) has been demonstrated to provide promising results in several challenging decision making and control tasks. However, the required inference costs of deep neural networks (DNNs) could prevent DRL from being applied to mobile robots which cannot afford high energy-consuming computations. To enable DRL methods to be affordable in such energy-limited platforms, we propose an asymmetric architecture that reduces the overall inference costs via switching between a computationally expensive policy and an economic one. The experimental results evaluated on a number of representative benchmark suites for robotic control tasks demonstrate that our method is able to reduce the inference costs while retaining the agent's overall performance.
