% @article{test-en,
% 	author = {Author},
% 	title = {Title},
% 	type = {J},
% 	journal = {Journal},
% 	date = {2014-04-01},
% 	language = {english},
% }

% @article{test-zh,
% 	author = {作者},
% 	title = {标题},
% 	type = {J},
% 	journal = {期刊},
% 	date = {2014-04-01},
% 	language = {chinese},
% }


@techreport{GSMA-2024,
	author = {James Joiner and Kenechi Okeleke and Sayali Borole and  Harry Fernando Aquije Ballon},
	title = {The Mobile Economy 2024},
	type = {R},
	institution = {GSMA Intelligence},
	year={2024},
	language = {english},
}


@ARTICLE{8410887,
  author={Qi, Chenhao and Wang, Xin},
  journal={IEEE Communications Letters}, 
  title={Precoding Design for Energy Efficiency of Multibeam Satellite Communications}, 
  year={2018},
  volume={22},
  number={9},
  pages={1826-1829},
  keywords={Satellites;Precoding;Approximation algorithms;Power demand;Quality of service;Feeds;Satellite antennas;Energy efficiency (EE);precoding design;satellite communications;multibeam satellite},
  doi={10.1109/LCOMM.2018.2855935}}
% vim:ts=4:sw=4

@article{mcdowell2020low,
  title={The low earth orbit satellite population and impacts of the SpaceX Starlink constellation},
  author={McDowell, Jonathan C},
  journal={The Astrophysical Journal Letters},
  volume={892},
  number={2},
  pages={L36},
  year={2020},
  publisher={IOP Publishing}
}

@incollection{henri2020oneweb,
  title={The OneWeb satellite system},
  author={Henri, Yvon},
  booktitle={Handbook of Small Satellites: Technology, Design, Manufacture, Applications, Economics and Regulation},
  pages={1091--1100},
  year={2020},
  publisher={Springer}
}

@article{leyva2022ngso,
  title={NGSO constellation design for global connectivity},
  author={Leyva-Mayorga, Israel and Soret, Beatriz and Matthiesen, Bho and R{\"o}per, Maik and W{\"u}bben, Dirk and Dekorsy, Armin and Popovski, Petar},
  journal={arXiv preprint arXiv:2203.16597},
  year={2022}
}

@inproceedings{jansson2022telesat,
  title={Telesat Lightspeed™-Enabling Mesh Network Solutions for Managed Data Service Flexibility Across the Globe},
  author={Jansson, Gerry},
  booktitle={2022 IEEE International Conference on Space Optical Systems and Applications (ICSOS)},
  pages={232--235},
  year={2022},
  organization={IEEE}
}

@article{osoro2021techno,
  title={A techno-economic framework for satellite networks applied to low earth orbit constellations: Assessing Starlink, OneWeb and Kuiper},
  author={Osoro, Ogutu B and Oughton, Edward J},
  journal={IEEE Access},
  volume={9},
  pages={141611--141625},
  year={2021},
  publisher={IEEE}
}
@article{阚茜2016衰落信道下波束卫星系统功率分配策略研究,
  title={衰落信道下波束卫星系统功率分配策略研究},
  author={阚茜},
  journal={合肥: 中国科学技术大学},
  year={2016}
}

@article{kaelbling1996reinforcement,
  title={Reinforcement learning: A survey},
  author={Kaelbling, Leslie Pack and Littman, Michael L and Moore, Andrew W},
  journal={Journal of artificial intelligence research},
  volume={4},
  pages={237--285},
  year={1996}
}

@book{russell2016artificial,
  title={Artificial intelligence: a modern approach},
  author={Russell, Stuart J and Norvig, Peter},
  year={2016},
  publisher={Pearson}
}

@book{sutton2018reinforcement,
  title={Reinforcement learning: An introduction},
  author={Sutton, Richard S and Barto, Andrew G},
  year={2018},
  publisher={MIT press}
}

@article{minsky1961steps,
  title={Steps toward artificial intelligence},
  author={Minsky, Marvin},
  journal={Proceedings of the IRE},
  volume={49},
  number={1},
  pages={8--30},
  year={1961},
  publisher={IEEE}
}

@incollection{morales2012introduction,
  title={An introduction to reinforcement learning},
  author={Morales, Eduardo F and Zaragoza, Julio H},
  booktitle={Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions},
  pages={63--80},
  year={2012},
  publisher={IGI Global}
}

@ARTICLE{7093179,
  author={Amin, Osama and Bedeer, Ebrahim and Ahmed, Mohamed Hossam and Dobre, Octavia A.},
  journal={IEEE Transactions on Vehicular Technology}, 
  title={Energy Efficiency–Spectral Efficiency Tradeoff: A Multiobjective Optimization Approach}, 
  year={2016},
  volume={65},
  number={4},
  pages={1975-1981},
  keywords={Linear programming;Optimization;OFDM;Power demand;Channel estimation;Complexity theory;Wireless communication;Energy efficiency;spectral efficiency;multiobjective optimization;OFDM;imperfect CSI;LMMSE;Energy efficiency (EE);imperfect channel state information (CSI);linear minimum mean square error (MMSE);multiobjective optimization;orthogonal frequency-division multiplexing (OFDM);spectral efficiency (SE)},
  doi={10.1109/TVT.2015.2425934}}

  @article{heliot2012energy,
  title={On the energy efficiency-spectral efficiency trade-off over the MIMO Rayleigh fading channel},
  author={H{\'e}liot, Fabien and Imran, Muhammad Ali and Tafazolli, Rahim},
  journal={IEEE Transactions on Communications},
  volume={60},
  number={5},
  pages={1345--1356},
  year={2012},
  publisher={IEEE}
}

@article{xiong2011energy,
  title={Energy-and spectral-efficiency tradeoff in downlink OFDMA networks},
  author={Xiong, Cong and Li, Geoffrey Ye and Zhang, Shunqing and Chen, Yan and Xu, Shugong},
  journal={IEEE transactions on wireless communications},
  volume={10},
  number={11},
  pages={3874--3886},
  year={2011},
  publisher={IEEE}
}

@book{tse2005fundamentals,
  title={Fundamentals of wireless communication},
  author={Tse, David and Viswanath, Pramod},
  year={2005},
  publisher={Cambridge university press}
}

@article{laursen2023no,
  title={No More “No Service”: Cellphones will increasingly text via satellite},
  author={Laursen, Lucas},
  journal={IEEE Spectrum},
  volume={60},
  number={1},
  pages={52--55},
  year={2023},
  publisher={IEEE}
}

@inproceedings{garey1974some,
  title={Some simplified NP-complete problems},
  author={Garey, Michael R and Johnson, David S and Stockmeyer, Larry},
  booktitle={Proceedings of the sixth annual ACM symposium on Theory of computing},
  pages={47--63},
  year={1974}
}

@article{choi2005optimum,
  title={Optimum power and beam allocation based on traffic demands and channel conditions over satellite downlinks},
  author={Choi, Jihwan P and Chan, Vincent WS},
  journal={IEEE Transactions on Wireless Communications},
  volume={4},
  number={6},
  pages={2983--2993},
  year={2005},
  publisher={IEEE}
}

@article{wang2014optimization,
  title={Optimization of power allocation for multiusers in multi-spot-beam satellite communication systems},
  author={Wang, Heng and Liu, Aijun and Pan, Xiaofei and Yang, Jianfei and others},
  journal={Mathematical Problems in engineering},
  volume={2014},
  year={2014},
  publisher={Hindawi}
}

@article{del1995efficient,
  title={Efficient dynamic channel allocation techniques with handover queuing for mobile satellite networks},
  author={Del Re, Enrico and Fantacci, Romano and Giambene, Giovanni},
  journal={IEEE Journal on Selected Areas in Communications},
  volume={13},
  number={2},
  pages={397--405},
  year={1995},
  publisher={IEEE}
}

@inproceedings{umehira2012centralized,
  title={Centralized dynamic channel assignment schemes for multi-beam mobile satellite communications systems},
  author={Umehira, Masahiro},
  booktitle={30th AIAA International Communications Satellite System Conference (ICSSC)},
  pages={15123},
  year={2012}
}

@article{liu2018deep,
  title={Deep reinforcement learning based dynamic channel allocation algorithm in multibeam satellite systems},
  author={Liu, Shuaijun and Hu, Xin and Wang, Weidong},
  journal={IEEE Access},
  volume={6},
  pages={15733--15742},
  year={2018},
  publisher={IEEE}
}
@inproceedings{ITUR6724,
  author          = {International Telecommunication Union},
  booktitle       = {ITU-R Recommendations incorprated by reference},
  editor          = {},
  title           = {RECOMMENDATION ITU-R S.672-4:
Satellite antenna radiation pattern for use as 
a design objective in the fixed-satellite service 
employing geostationary satellites },
  year            = {1997}
}

@article{series2015propagation,
  title={Propagation data and prediction methods required for the design of Earth-space telecommunication systems},
  author={Series, P},
  year={2023}
}

@article{garcia2013markov,
  title={Markov decision processes},
  author={Garcia, Fr{\'e}d{\'e}rick and Rachelson, Emmanuel},
  journal={Markov Decision Processes in Artificial Intelligence},
  pages={1--38},
  year={2013},
  publisher={Wiley Online Library}
}

@article{hart1968formal,
  title={A formal basis for the heuristic determination of minimum cost paths},
  author={Hart, Peter E and Nilsson, Nils J and Raphael, Bertram},
  journal={IEEE transactions on Systems Science and Cybernetics},
  volume={4},
  number={2},
  pages={100--107},
  year={1968},
  publisher={IEEE}
}
@inproceedings{luis2019deep,
  title={Deep reinforcement learning for continuous power allocation in flexible high throughput satellites},
  author={Luis, Juan Jose Garau and Guerster, Markus and del Portillo, Inigo and Crawley, Edward and Cameron, Bruce},
  booktitle={2019 ieee cognitive communications for aerospace applications workshop (ccaaw)},
  pages={1--4},
  year={2019},
  organization={IEEE}
}

@article{mnih2013playing,
  title={Playing atari with deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
  journal={arXiv preprint arXiv:1312.5602},
  year={2013}
}
@article{schulman2017proximal,
  title={Proximal policy optimization algorithms},
  author={Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
  journal={arXiv preprint arXiv:1707.06347},
  year={2017}
}

@article{lin2022dynamic,
  title={Dynamic beam pattern and bandwidth allocation based on multi-agent deep reinforcement learning for beam hopping satellite systems},
  author={Lin, Zhiyuan and Ni, Zuyao and Kuang, Linling and Jiang, Chunxiao and Huang, Zhen},
  journal={IEEE Transactions on Vehicular Technology},
  volume={71},
  number={4},
  pages={3917--3930},
  year={2022},
  publisher={IEEE}
}
@article{hu2020dynamic,
  title={Dynamic beam hopping method based on multi-objective deep reinforcement learning for next generation satellite broadband systems},
  author={Hu, Xin and Zhang, Yuchen and Liao, Xianglai and Liu, Zhijun and Wang, Weidong and Ghannouchi, Fadhel M},
  journal={IEEE Transactions on Broadcasting},
  volume={66},
  number={3},
  pages={630--646},
  year={2020},
  publisher={IEEE}
}

@inproceedings{angeletti2006beam,
  title={Beam hopping in multi-beam broadband satellite systems: System performance and payload architecture analysis},
  author={Angeletti, Piero and Fernandez Prim, David and Rinaldo, Rita},
  booktitle={24th aiaa international communications satellite systems conference},
  pages={5376},
  year={2006}
}
@article{liu2013max,
  title={Max-min rate control on traffic in broadband multibeam satellite communications systems},
  author={Liu, Hongying and Yang, Zhiming and Cao, Zhigang},
  journal={IEEE Communications letters},
  volume={17},
  number={7},
  pages={1396--1399},
  year={2013},
  publisher={IEEE}
}
@article{han2015qos,
  title={QoS-equilibrium slot allocation for beam hopping in broadband satellite communication systems},
  author={Han, Han and Zheng, Xueqiang and Huang, Qinfei and Lin, Yuan},
  journal={Wireless Networks},
  volume={21},
  pages={2617--2630},
  year={2015},
  publisher={Springer}
}
@ARTICLE{9210133,
  author={Hassan, Naveed U.L. and Huang, Chongwen and Yuen, Chau and Ahmad, Ayaz and Zhang, Yan},
  journal={IEEE Wireless Communications}, 
  title={Dense Small Satellite Networks for Modern Terrestrial Communication Systems: Benefits, Infrastructure, and Technologies}, 
  year={2020},
  volume={27},
  number={5},
  pages={96-103},
  keywords={Small satellites;Low earth orbit satellites;Satellite broadcasting;Planetary orbits},
  doi={10.1109/MWC.001.1900394}}

  @article{唐斯琪2023深度强化学习在天基信息网络中的应用,
  title={深度强化学习在天基信息网络中的应用——现状与前景},
  author={唐斯琪 and 潘志松 and 胡谷雨 and 吴炀 and 李云波},
  journal={系统工程与电子技术},
  volume={45},
  number={3},
  pages={886--901},
  year={2023}
}

@inproceedings{wang2021joint,
  title={Joint beam-hopping scheduling and power allocation in NOMA-assisted satellite systems},
  author={Wang, Anyue and Lei, Lei and Lagunas, Eva and Chatzinotas, Symeon and Neira, Ana Isabel P{\'e}rez and Ottersten, Bj{\"o}rn},
  booktitle={2021 ieee wireless communications and networking conference (wcnc)},
  pages={1--6},
  year={2021},
  organization={IEEE}
}
@inproceedings{panthi2017beam,
  title={Beam hopping-a flexible satellite communication system for mobility},
  author={Panthi, Sunil and Breynaert, Dirk and McLain, Christopher and King, Janet},
  booktitle={35th AIAA International Communications Satellite Systems Conference},
  pages={5413},
  year={2017}
}

@article{zhao2020deep,
  title={A deep reinforcement learning based approach for energy-efficient channel allocation in satellite Internet of Things},
  author={Zhao, Baokang and Liu, Jiahao and Wei, Ziling and You, Ilsun},
  journal={IEEE Access},
  volume={8},
  pages={62197--62206},
  year={2020},
  publisher={IEEE}
}


@article{etsi2005digital,
  title={Digital video broadcasting (dvb); second generation framing structure, channel coding and modulation systems for broadcasting, interactive services, news gathering and other broadband satellite applications},
  author={ETSI, ETSI},
  journal={Part II: S2-Extensions (DVB-S2X)},
  pages={22--27},
  year={2005}
}

@book{ilvcev2017global,
  title={Global Mobile Satellite Communications Theory},
  author={Il{\v{c}}ev, Stoj{\v{c}}e Dimov},
  year={2017},
  publisher={Springer}
}

@article{张沛2020基于深度增强学习和多目标优化改进的卫星资源分配算法,
  title={基于深度增强学习和多目标优化改进的卫星资源分配算法},
  author={张沛 and 刘帅军 and 马治国 and 王晓晖 and 宋俊德},
  journal={Journal on Communication/Tongxin Xuebao},
  volume={41},
  number={6},
  year={2020}
}

@mastersthesis{张雨晨2020基于多目标深度强化学习的多波束卫星动态波束调度算法研究,
  title={基于多目标深度强化学习的多波束卫星动态波束调度算法研究},
  author={张雨晨},
  year={2020},
  school={北京邮电大学}
}

@article{刘刚2004卫星蜂窝通信系统中的点波束设计,
  title={卫星蜂窝通信系统中的点波束设计},
  author={刘刚 and 吴诗其},
  journal={系统工程与电子技术},
  volume={26},
  number={2},
  pages={157--159},
  year={2004}
}
@phdthesis{低轨卫星通信网络中面向多星协作的资源分配研究,
  author      = {赵梅惠},
  school      = {北京大学},
  title       = {低轨卫星通信网络中面向多星协作的资源分配研究},
  year        = {2024}
}

@article{bai2018multi,
  title={Multi-satellite relay transmission in 5G: Concepts, techniques, and challenges},
  author={Bai, Lin and Zhu, Lina and Zhang, Xuejun and Zhang, Wei and Yu, Quan},
  journal={IEEE Network},
  volume={32},
  number={5},
  pages={38--44},
  year={2018},
  publisher={IEEE}
}
@article{jia2018interbeam,
  title={Interbeam interference constrained resource allocation for shared spectrum multibeam satellite communication systems},
  author={Jia, Min and Zhang, Ximu and Gu, Xuemai and Guo, Qing and Li, Yaqiu and Lin, Ping},
  journal={IEEE Internet of Things Journal},
  volume={6},
  number={4},
  pages={6052--6059},
  year={2018},
  publisher={IEEE}
}

@article{yang2003co,
  title={Co-channel interference modeling and analysis in a Poisson field of interferers in wireless communications},
  author={Yang, Xueshi and Petropulu, Athina P},
  journal={IEEE Transactions on signal processing},
  volume={51},
  number={1},
  pages={64--76},
  year={2003},
  publisher={IEEE}
}

@article{甘仲民2006卫星通信技术的新发展,
  title={卫星通信技术的新发展},
  author={甘仲民 and 张更新},
  journal={通信学报},
  volume={8},
  year={2006}
}
@article{kreutel1977antenna,
  title={Antenna technology for frequency reuse satellite communications},
  author={Kreutel, RW and Difonzo, DF and English, WJ and Gruner, RW},
  journal={Proceedings of the IEEE},
  volume={65},
  number={3},
  pages={370--378},
  year={1977},
  publisher={IEEE}
}

@article{周碧莹2019基于强化学习的卫星网络资源调度机制,
  title={基于强化学习的卫星网络资源调度机制.},
  author={周碧莹 and 王爱平 and 费长江 and 虞万荣 and 赵宝康},
  journal={Computer Engineering \& Science/Jisuanji Gongcheng yu Kexue},
  volume={41},
  number={12},
  year={2019}
}

@article{刘召2019多波束卫星动态信道资源分配算法,
  title={多波束卫星动态信道资源分配算法},
  author={刘召 and 许珂},
  journal={移动通信},
  volume={43},
  number={5},
  pages={27--32},
  year={2019}
}

@article{刘帅军2018卫星通信系统中动态资源管理技术研究,
  title={卫星通信系统中动态资源管理技术研究},
  author={刘帅军},
  journal={北京: 北京邮电大学},
  year={2018}
}

@book{wxtxxt,

author={朱立东 and 李成杰 and 张勇 and 骆忠强},

year={2020},

title={卫星通信系统及应用},

publisher={科学出版社},

address={北京},

isbn={703065093X;9787030650931;},

language={Chinese},

}

@article{张汝波2000强化学习理论,
  title={强化学习理论, 算法及应用},
  author={张汝波 and 顾国昌 and 刘照德 and 王醒策},
  journal={控制理论与应用},
  volume={17},
  number={5},
  pages={637--642},
  year={2000}
}

@article{尚玉昌2006动物的试,
  title={动物的试-错学习行为},
  author={尚玉昌},
  journal={生物学通报},
  volume={41},
  number={1},
  pages={11--13},
  year={2006}
}

@article{booker1989classifier,
  title={Classifier systems and genetic algorithms},
  author={Booker, Lashon B. and Goldberg, David E. and Holland, John H.},
  journal={Artificial intelligence},
  volume={40},
  number={1-3},
  pages={235--282},
  year={1989},
  publisher={Elsevier}
}

@article{陈华根2004模拟退火算法机理研究,
  title={模拟退火算法机理研究},
  author={陈华根 and 吴健生 and 王家林 and 陈冰},
  journal={同济大学学报: 自然科学版},
  volume={32},
  number={6},
  pages={802--805},
  year={2004}
}
@article{xiong2019deep,
  title={Deep reinforcement learning for mobile 5G and beyond: Fundamentals, applications, and challenges},
  author={Xiong, Zehui and Zhang, Yang and Niyato, Dusit and Deng, Ruilong and Wang, Ping and Wang, Li-Chun},
  journal={IEEE Vehicular Technology Magazine},
  volume={14},
  number={2},
  pages={44--52},
  year={2019},
  publisher={IEEE}
}

@article{纪明星2018天通一号卫星移动通信系统市场及应用分析,
  title={天通一号卫星移动通信系统市场及应用分析},
  author={纪明星},
  journal={卫星与网络},
  volume={4},
  pages={42--43},
  year={2018}
}

@article{徐冰玉2021starlink,
  title={Starlink 低轨卫星通信星座深度分析},
  author={徐冰玉 and 李侠宇},
  journal={信息通信技术与政策},
  volume={47},
  number={9},
  pages={16},
  year={2021}
}

@article{johnson1928thermal,
  title={Thermal agitation of electricity in conductors},
  author={Johnson, John Bertrand},
  journal={Physical review},
  volume={32},
  number={1},
  pages={97},
  year={1928},
  publisher={APS}
}

@book{littman1996algorithms,
  title={Algorithms for sequential decision-making},
  author={Littman, Michael Lederman},
  year={1996},
  publisher={Brown University}
}

@article{bellman1966dynamic,
  title={Dynamic programming},
  author={Bellman, Richard},
  journal={science},
  volume={153},
  number={3731},
  pages={34--37},
  year={1966},
  publisher={American Association for the Advancement of Science}
}

@article{puterman1990markov,
  title={Markov decision processes},
  author={Puterman, Martin L},
  journal={Handbooks in operations research and management science},
  volume={2},
  pages={331--434},
  year={1990},
  publisher={Elsevier}
}

@article{konda1999actor,
  title={Actor-critic algorithms},
  author={Konda, Vijay and Tsitsiklis, John},
  journal={Advances in neural information processing systems},
  volume={12},
  year={1999}
}

@inproceedings{silver2014deterministic,
  title={Deterministic policy gradient algorithms},
  author={Silver, David and Lever, Guy and Heess, Nicolas and Degris, Thomas and Wierstra, Daan and Riedmiller, Martin},
  booktitle={International conference on machine learning},
  pages={387--395},
  year={2014},
  organization={Pmlr}
}

@article{lillicrap2015continuous,
  title={Continuous control with deep reinforcement learning},
  author={Lillicrap, Timothy P and Hunt, Jonathan J and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
  journal={arXiv preprint arXiv:1509.02971},
  year={2015}
}
@article{mnih2015human,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
  journal={nature},
  volume={518},
  number={7540},
  pages={529--533},
  year={2015},
  publisher={Nature Publishing Group UK London}
}
@inproceedings{van2016deep,
  title={Deep reinforcement learning with double q-learning},
  author={Van Hasselt, Hado and Guez, Arthur and Silver, David},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={30},
  number={1},
  year={2016}
}

@inproceedings{wang2016dueling,
  title={Dueling network architectures for deep reinforcement learning},
  author={Wang, Ziyu and Schaul, Tom and Hessel, Matteo and Hasselt, Hado and Lanctot, Marc and Freitas, Nando},
  booktitle={International conference on machine learning},
  pages={1995--2003},
  year={2016},
  organization={PMLR}
}

@inproceedings{mnih2016asynchronous,
  title={Asynchronous methods for deep reinforcement learning},
  author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
  booktitle={International conference on machine learning},
  pages={1928--1937},
  year={2016},
  organization={PMLR}
}

@article{schulman2017proximal,
  title={Proximal policy optimization algorithms},
  author={Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
  journal={arXiv preprint arXiv:1707.06347},
  year={2017}
}
@inproceedings{fujimoto2018addressing,
  title={Addressing function approximation error in actor-critic methods},
  author={Fujimoto, Scott and Hoof, Herke and Meger, David},
  booktitle={International conference on machine learning},
  pages={1587--1596},
  year={2018},
  organization={PMLR}
}

@inproceedings{haarnoja2018soft,
  title={Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor},
  author={Haarnoja, Tuomas and Zhou, Aurick and Abbeel, Pieter and Levine, Sergey},
  booktitle={International conference on machine learning},
  pages={1861--1870},
  year={2018},
  organization={PMLR}
}

@article{he2013water,
  title={Water-filling: A geometric approach and its application to solve generalized radio resource allocation problems},
  author={He, Peter and Zhao, Lian and Zhou, Sheng and Niu, Zhisheng},
  journal={IEEE transactions on Wireless Communications},
  volume={12},
  number={7},
  pages={3637--3647},
  year={2013},
  publisher={IEEE}
}

@mastersthesis{杨宇龙2020多波束卫星通信系统的资源分配算法研究,
  title={多波束卫星通信系统的资源分配算法研究},
  author={杨宇龙},
  year={2020},
  school={哈尔滨工程大学}
}