Chengxing Jia, Fuxiang Zhang, Tian Xu, Jing-Cheng Pang, Zongzhang Zhang, Yang Yu 0001. Model gradient: unified model and policy learning in model-based reinforcement learning. Frontiers of Computer Science in China, 18(4):184339, August 2024. [doi]
@article{JiaZXPZY24,
title = {Model gradient: unified model and policy learning in model-based reinforcement learning},
author = {Chengxing Jia and Fuxiang Zhang and Tian Xu and Jing-Cheng Pang and Zongzhang Zhang and Yang Yu 0001},
year = {2024},
month = {August},
doi = {10.1007/s11704-023-3150-5},
url = {https://doi.org/10.1007/s11704-023-3150-5},
researchr = {https://researchr.org/publication/JiaZXPZY24},
cites = {0},
citedby = {0},
journal = {Frontiers of Computer Science in China},
volume = {18},
number = {4},
pages = {184339},
}