{"type":"ScholarlyArticle","title":"DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning","authors":[{"name":"Canzhe Zhao","slug":"canzhe-zhao","given":"Canzhe","family":"Zhao","affiliation":"Center for Computer Science , Shanghai Jiao Tong University"},{"name":"Yanjie Ze","slug":"yanjie-ze","given":"Yanjie","family":"Ze","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Jing Dong","slug":"jing-dong","given":"Jing","family":"Dong","affiliation":"School of Data Science , The Chinese University of Hong Kong , Shenzhen"},{"name":"Baoxiang Wang","slug":"baoxiang-wang","given":"Baoxiang","family":"Wang","affiliation":"School of Data Science , The Chinese University of Hong Kong , Shenzhen"},{"name":"Shuai Li","slug":"shuai-li","given":"Shuai","family":"Li","affiliation":"Center for Computer Science , Shanghai Jiao Tong University"}],"abstract":"Communication lays the foundation for cooperation in human society and in multi-agent reinforcement learning (MARL). Humans also desire to maintain their privacy when communicating with others, yet such privacy concern has not been considered in existing works in MARL. We propose the differentially private multi-agent communication (DPMAC) algorithm, which protects the sensitive information of individual agents by equipping each agent with a local message sender with rigorous (epsilon, delta)-differential privacy (DP) guarantee. In contrast to directly perturbing the messages with predefined DP noise as commonly done in privacy-preserving scenarios, we adopt a stochastic message sender for each agent respectively and incorporate the DP requirement into the sender, which automatically adjusts the learned message distribution to alleviate the instability caused by DP noise. Further, we prove the existence of a Nash equilibrium in cooperative MARL with privacy-preserving communication, which suggests that this problem is game-theoretically learnable. Extensive experiments demonstrate a clear advantage of DPMAC over baseline methods in privacy-preserving scenarios.","doi":"10.24963/ijcai.2023/516","url":"https://ijcai.org/proceedings/2023/516","pdf":"https://ijcai.org/proceedings/2023/0516.pdf","markdown":"https://ijcai.org/proceedings/2023/516.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/516","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":516,"pages":{"first":4638,"last":4646},"keywords":["Agent-based and Multi-agent Systems: MAS: Agent communication","Machine Learning: ML: Deep reinforcement learning"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2016] Martin Abadi, Andy Chu, Ian Goodfel- low, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. Deep learning with differential privacy. In ACM CCS, 2016.","title":"Deep learning with differential privacy","authors":"Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan Mcmahan, Ilya Mironov, Kunal Talwar, Li Zhang","year":"2016","venue":"ACM CCS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Alvim et al., 2011] Mário S Alvim, Miguel E Andrés, Kon- stantinos Chatzikokolakis, Pierpaolo Degano, and Catus- cia Palamidessi. Differential privacy: on the trade-off between utility and information leakage. In Interna- tional Workshop on Formal Aspects in Security and Trust. Springer, 2011.","title":"Differential privacy: on the trade-off between utility and information leakage","authors":"Miguel E Mário S Alvim, Konstantinos Andrés, Pierpaolo Chatzikokolakis, Catuscia Degano, Palamidessi","year":"2011","venue":"International Workshop on Formal Aspects in Security and Trust","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Balle et al., 2016] Borja Balle, Maziar Gomrokchi, and Doina Precup. Differentially private policy evaluation. In ICML. PMLR, 2016.","title":"Differentially private policy evaluation","authors":"Borja Balle, Maziar Gomrokchi, Doina Precup","year":"2016","venue":"ICML. PMLR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Beimel et al., 2008] Amos Beimel, Kobbi Nissim, and Eran Omri. Distributed private data analysis: Simultaneously solving how and what. In Advances in Cryptology - CRYPTO 2008. Springer, 2008.","title":"Distributed private data analysis: Simultaneously solving how and what","authors":"Beimel","year":"2008","venue":"Advances in Cryptology -CRYPTO 2008","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2020] Dingfan Chen, Tribhuvanesh Orekondy, and Mario Fritz. GS-WGAN: A gradient-sanitized ap- proach for learning differentially private generators. In NeurIPS 33, 2020.","title":"GS-WGAN: A gradient-sanitized approach for learning differentially private generators","authors":"Chen","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheu, 2021] Albert Cheu. Differential privacy in the shuffle model: A survey of separations. arXiv:2107.11839, 2021.","title":"Differential privacy in the shuffle model: A survey of separations","authors":"Albert Cheu, Cheu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Das et al., 2019] Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Mike Rabbat, and Joelle Pineau. Tarmac: Targeted multi-agent communi- cation. In ICML 2019. PMLR, 2019.","title":"Tarmac: Targeted multi-agent communication","authors":"Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Mike Rabbat, Joelle Pineau","year":"2019","venue":"ICML 2019","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2020] Ziluo Ding, Tiejun Huang, and Zongqing Lu. Learning individually inferred communication for multi-agent cooperation. In NeurIPS 33, 2020.","title":"Learning individually inferred communication for multi-agent cooperation","authors":"Ding","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dong et al., 2020] Tao Dong, Xiangyu Bu, and Wenjie Hu. Distributed differentially private average consensus for multi-agent networks by additive functional laplace noise. Journal of the Franklin Institute, (6), 2020.","title":"Distributed differentially private average consensus for multi-agent networks by additive functional laplace noise","authors":"Tao Dong, Xiangyu Bu, Wenjie Hu","year":"2020","venue":"Journal of the Franklin Institute","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dubey and Pentland, 2020] Abhimanyu Dubey and Alex 'Sandy' Pentland. Differentially-private feder- ated linear bandits. In NeurIPS 33, 2020.","title":"Differentially-private federated linear bandits","authors":"Abhimanyu Dubey, Alex 'sandy' Pentland","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dubey, 2021] Abhimanyu Dubey. No-regret algorithms for private gaussian process bandit optimization. In AISTATS 2021. PMLR, 2021.","title":"No-regret algorithms for private gaussian process bandit optimization","authors":"Abhimanyu Dubey","year":"2021","venue":"AISTATS 2021","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dwork et al., 2014] Cynthia Dwork, Aaron Roth, et al. The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci., (3-4), 2014.","title":"The algorithmic foundations of differential privacy","authors":"Cynthia Dwork, Aaron Roth","year":"2014","venue":"Found. Trends Theor. Comput. Sci","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dwork, 2006] Cynthia Dwork. Differential privacy. In ICALP. Springer, 2006.","title":"Differential privacy","authors":"Cynthia Dwork","year":"2006","venue":"ICALP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Foerster et al., 2016] Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, and Shimon Whiteson. Learning to communicate with deep multi-agent reinforcement learn- ing. In NeurIPS 29, 2016.","title":"Learning to communicate with deep multi-agent reinforcement learning","authors":"Jakob N Foerster, M Yannis, Nando Assael, Shimon De Freitas, Whiteson","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Garcelon et al., 2021] Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, and Matteo Pirotta. Local differential privacy for regret minimization in reinforcement learning. In NeurIPS 34, 2021.","title":"Local differential privacy for regret minimization in reinforcement learning","authors":"Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, Matteo Pirotta","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hassan et al., 2020] Muneeb Ul Hassan, Mubashir Husain Rehmani, and Jinjun Chen. Differential privacy techniques for cyber physical systems: A survey. IEEE Commun. Surv. Tutorials, 2020.","title":"Differential privacy techniques for cyber physical systems: A survey","authors":"Mubashir Muneeb Ul Hassan, Jinjun Husain Rehmani, Chen","year":"2020","venue":"IEEE Commun. Surv. Tutorials","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Jiang and Lu, 2018] Jiechuan Jiang and Zongqing Lu. Learning attentional communication for multi-agent coop- eration. In NeurIPS 31, 2018.","title":"Learning attentional communication for multi-agent cooperation","authors":"Lu ; Jiang, Jiechuan Jiang, Zongqing Lu","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kim et al., 2021] Woojun Kim, Jongeui Park, and Youngchul Sung. Communication in multi-agent re- inforcement learning: Intention sharing. In ICLR, 2021.","title":"Communication in multi-agent reinforcement learning: Intention sharing","authors":"Kim","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Leonardos et al., 2021] Stefanos Leonardos, Will Overman, Ioannis Panageas, and Georgios Piliouras. Global conver- gence of multi-agent policy gradient in markov potential games. arXiv:2106.01969, 2021.","title":"Global convergence of multi-agent policy gradient in markov potential games","authors":"Stefanos Leonardos, Will Overman, Ioannis Panageas, Georgios Piliouras","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2021] Ziyan Li, Quan Yuan, Guiyang Luo, and Jinglin Li. Learning effective multi-vehicle cooperation at unsignalized intersection via bandwidth-constrained com- munication. In 94th IEEE Vehicular Technology Confer- ence, VTC 2021. IEEE, 2021.","title":"Learning effective multi-vehicle cooperation at unsignalized intersection via bandwidth-constrained communication","authors":"Ziyan Li, Quan Yuan, Guiyang Luo, Jinglin Li","year":"2021","venue":"94th IEEE Vehicular Technology Conference","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Liao et al., 2021] Chonghua Liao, Jiafan He, and Quanquan Gu. Locally differentially private reinforcement learn- ing for linear mixture markov decision processes. arXiv preprint arXiv:2110.10133, 2021.","title":"Locally differentially private reinforcement learning for linear mixture markov decision processes","authors":"Liao","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lin et al., 2021] Toru Lin, Jacob Huh, Christopher Stauffer, Ser-Nam Lim, and Phillip Isola. Learning to ground multi- agent communication with autoencoders. In NeurIPS 34, 2021.","title":"Learning to ground multiagent communication with autoencoders","authors":"Toru Lin, Jacob Huh, Christopher Stauffer, Ser-Nam Lim, Phillip Isola","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lowe et al., 2017] Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, and Igor Mordatch. Multi-agent actor-critic for mixed cooperative-competitive environ- ments. In NeurIPS 30, 2017.","title":"Multi-agent actor-critic for mixed cooperative-competitive environments","authors":"Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Macua et al., 2018] Sergio Valcarcel Macua, Javier Zazo, and Santiago Zazo. Learning parametric closed-loop poli- cies for markov potential games. In ICLR, 2018.","title":"Learning parametric closed-loop policies for markov potential games","authors":"Sergio Valcarcel Macua, Javier Zazo, Santiago Zazo","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Monderer and Shapley, 1996] Dov Monderer and Lloyd S Shapley. Potential games. Games and economic behav- ior, 1996.","title":"Potential games. Games and economic behavior","authors":"Shapley Monderer, Dov Monderer, Lloyd S Shapley","year":"1996","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mordatch and Abbeel, 2017] Igor Mordatch and Pieter Abbeel. Emergence of grounded compositional language in multi-agent populations. arXiv:1703.04908, 2017.","title":"Igor Mordatch and Pieter Abbeel. Emergence of grounded compositional language in multi-agent populations","authors":"Abbeel Mordatch","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Peng et al., 2017] Peng Peng, Quan Yuan, Ying Wen, Yaodong Yang, Zhenkun Tang, Haitao Long, and Jun Wang. Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games. CoRR, abs/1703.10069, 2017.","title":"Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games","authors":"Peng Peng, Quan Yuan, Ying Wen, Yaodong Yang, Zhenkun Tang, Haitao Long, Jun Wang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Rangwala and Williams, 2020] Murtaza Rangwala and Ryan Williams. Learning multi-agent communication through structured attentive reasoning. In NeurIPS 33, 2020.","title":"Learning multi-agent communication through structured attentive reasoning","authors":"Murtaza Rangwala, Ryan Williams","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sakuma et al., 2008] Jun Sakuma, Shigenobu Kobayashi, and Rebecca N Wright. Privacy-preserving reinforcement learning. In ICML, 2008.","title":"Privacy-preserving reinforcement learning","authors":"Sakuma","year":"2008","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shalev-Shwartz et al., 2016] Shai Shalev-Shwartz, Shaked Shammah, and Amnon Shashua. Safe, multi-agent, re- inforcement learning for autonomous driving. CoRR, abs/1610.03295, 2016.","title":"Safe, multi-agent, reinforcement learning for autonomous driving","authors":"Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Singh et al., 2019] Amanpreet Singh, Tushar Jain, and Sainbayar Sukhbaatar. Learning when to communicate at scale in multiagent cooperative and competitive tasks. In ICLR, 2019.","title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","authors":"Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Sukhbaatar et al., 2016] Sainbayar Sukhbaatar, Arthur Szlam, and Rob Fergus. Learning multiagent com- munication with backpropagation. In NeurIPS 29, 2016.","title":"Learning multiagent communication with backpropagation","authors":"Sukhbaatar","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Sutton et al., 1999] Richard S. Sutton, David A. McAllester, Satinder P. Singh, and Yishay Mansour. Policy gradient methods for reinforcement learning with function approximation. In NeurIPS 12, 1999.","title":"Policy gradient methods for reinforcement learning with function approximation","authors":"Richard S Sutton, David A Mcallester, P Satinder, Yishay Singh, Mansour","year":"1999","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Tao et al., 2022] Youming Tao, Yulian Wu, Peng Zhao, and Di Wang. Optimal rates of (locally) differentially private heavy-tailed multi-armed bandits. In AISTATS. PMLR, 2022.","title":"Optimal rates of (locally) differentially private heavy-tailed multi-armed bandits","authors":"Youming Tao, Yulian Wu, Peng Zhao, Di Wang","year":"2022","venue":"AISTATS. PMLR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Tenenbaum et al., 2021] Jay Tenenbaum, Haim Kaplan, Yishay Mansour, and Uri Stemmer. Differentially private multi-armed bandits in the shuffle model. In NeurIPS 34, 2021.","title":"Differentially private multi-armed bandits in the shuffle model","authors":"Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Tian et al., 2021] Qi Tian, Kun Kuang, Baoxiang Wang, Fu- rui Liu, and Fei Wu. Multi-agent communication with graph information bottleneck under limited bandwidth. CoRR, abs/2112.10374, 2021.","title":"Multi-agent communication with graph information bottleneck under limited bandwidth","authors":"Qi Tian, Kun Kuang, Baoxiang Wang, Furui Liu, Fei Wu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Tossou and Dimitrakakis, 2017] Aristide Charles Yedia Tossou and Christos Dimitrakakis. Achieving privacy in the adversarial multi-armed bandit. In AAAI, 2017.","title":"Aristide Charles Yedia Tossou and Christos Dimitrakakis. Achieving privacy in the adversarial multi-armed bandit","authors":"Dimitrakakis Tossou","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Tucker et al., 2022] Mycal Tucker, Julie Shah, Roger Levy, and Noga Zaslavsky. Towards human-agent communi- cation via the information bottleneck principle. CoRR, abs/2207.00088, 2022.","title":"Towards human-agent communication via the information bottleneck principle","authors":"Mycal Tucker, Julie Shah, Roger Levy, Noga Zaslavsky","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wang and Hegde, 2019] Baoxiang Wang and Nidhi Hegde. Privacy-preserving q-learning with functional noise in continuous spaces. NeurIPS, 2019.","title":"Privacy-preserving q-learning with functional noise in continuous spaces","authors":"Wang, Hegde ;, Baoxiang Wang, Nidhi Hegde","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Wang et al., 2020a] Rundong Wang, Xu He, Runsheng Yu, Wei Qiu, Bo An, and Zinovi Rabinovich. Learning effi- cient multi-agent communication: An information bottle- neck approach. In ICML 2020. PMLR, 2020.","title":"Learning efficient multi-agent communication: An information bottleneck approach","authors":"Wang","year":"2020","venue":"ICML 2020","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wang et al., 2020b] Tonghan Wang, Jianhao Wang, Chongyi Zheng, and Chongjie Zhang. Learning nearly decomposable value functions via communication minimization. In ICLR, 2020.","title":"Learning nearly decomposable value functions via communication minimization","authors":"Wang","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Wei et al., 2019] Hua Wei, Nan Xu, Huichu Zhang, Guanjie Zheng, Xinshi Zang, Chacha Chen, Weinan Zhang, Yan- min Zhu anda Kai Xu, and Zhenhui Li. Colight: Learn- ing network-level cooperation for traffic signal control. In ACM CIKM, 2019.","title":"Colight: Learning network-level cooperation for traffic signal control","authors":"Hua Wei, Nan Xu, Huichu Zhang, Guanjie Zheng, Xinshi Zang, Chacha Chen, Weinan Zhang, Yanmin Zhu, Kai Xu, Zhenhui Li","year":"2019","venue":"ACM CIKM","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Yang et al., 2020] Jiachen Yang, Alireza Nakhaei, David Isele, Kikuo Fujimura, and Hongyuan Zha. CM3: coop- erative multi-goal multi-stage multi-agent reinforcement learning. In ICLR, 2020.","title":"CM3: cooperative multi-goal multi-stage multi-agent reinforcement learning","authors":"Yang","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Ye et al., 2020] Dayong Ye, Tianqing Zhu, Zishuo Cheng, Wanlei Zhou, and S Yu Philip. Differential advising in multiagent reinforcement learning. IEEE Transactions on Cybernetics, 2020.","title":"Differential advising in multiagent reinforcement learning","authors":"Dayong Ye, Tianqing Zhu, Zishuo Cheng, Wanlei Zhou, S Yu, Philip","year":"2020","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang and Lesser, 2011] Chongjie Zhang and Victor R. Lesser. Coordinated multi-agent reinforcement learning in networked distributed pomdps. In AAAI, 2011.","title":"Coordinated multi-agent reinforcement learning in networked distributed pomdps","authors":"Lesser Zhang, Chongjie Zhang, Victor R Lesser","year":"2011","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhang et al., 2019] Sai Qian Zhang, Qi Zhang, and Jieyu Lin. Efficient communication in multi-agent reinforce- ment learning via variance based control. In NeurIPS 32, 2019.","title":"Efficient communication in multi-agent reinforcement learning via variance based control","authors":"Qi Sai Qian Zhang, Jieyu Zhang, Lin","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhang et al., 2020] Sai Qian Zhang, Qi Zhang, and Jieyu Lin. Succinct and robust multi-agent communication with temporal message control. In NeurIPS 33, 2020.","title":"Succinct and robust multi-agent communication with temporal message control","authors":"Qi Sai Qian Zhang, Jieyu Zhang, Lin","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhang et al., 2021] Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, and Songtao Lu. Taming communica- tion and sample complexities in decentralized policy eval- uation for cooperative multi-agent reinforcement learning. In NeurIPS 34, 2021.","title":"Taming communication and sample complexities in decentralized policy evaluation for cooperative multi-agent reinforcement learning","authors":"Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, Songtao Lu","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Zheng et al., 2020] Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, and Liwei Wang. Locally differentially pri- vate (contextual) bandits learning. In NeurIPS 33, 2020.","title":"Locally differentially private (contextual) bandits learning","authors":"Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Liwei Wang","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Zhou, 2022] Xingyu Zhou. Differentially private reinforce- ment learning with linear function approximation. Proc. ACM Meas. Anal. Comput. Syst., 2022.","title":"Differentially private reinforcement learning with linear function approximation","authors":"Xingyu Zhou, Zhou","year":"2022","venue":"Proc. ACM Meas. Anal. Comput. Syst","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}