no code implementations • 15 Nov 2022 • Yunfan Zhou, Xijun Li, Qingyu Qu
Offline reinforcement learning (RL) defines a sample-efficient learning paradigm, where a policy is learned from static and previously collected datasets without additional interaction with the environment.
no code implementations • 2 Feb 2022 • Qingyu Qu, Xijun Li, Yunfan Zhou
Combinatorial optimization problems have aroused extensive research interests due to its huge application potential.
no code implementations • 17 Jan 2022 • Xijun Li, Qingyu Qu, Fangzhou Zhu, Jia Zeng, Mingxuan Yuan, Kun Mao, Jie Wang
In the past decades, a serial of traditional operation research algorithms have been proposed to obtain the optimum of a given LP in a fewer solving time.
no code implementations • 17 Jan 2022 • Qingyu Qu, Xijun Li, Yunfan Zhou, Jia Zeng, Mingxuan Yuan, Jie Wang, Jinhu Lv, Kexin Liu, Kun Mao
Similar to offline reinforcement learning, we initially train on the demonstration data to accelerate learning massively.