Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture

Chin-Jui ChangYu-Wei ChuChao-Hsien TingHao-Kang LiuZhang-Wei HongChun-Yi Lee2024-10-292024-10-292021-05-30https://scholars.lib.ntu.edu.tw/handle/123456789/722586Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architectureconference paper10.1109/icra48506.2021.9562026