Publication
A complete list of papers is on Google Scholar
See The Gambler's Problem and Beyond for my most representative work
Conference papers
-
Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games [pdf]
Jing Dong, Baoxiang Wang, Yaoliang Yu.
International Conference on Artificial Intelligence and Statistics (AISTATS) 2024.
-
On Stationary Point Convergence of PPO-Clip [pdf]
Ruinan Jin, Shuai Li, Baoxiang Wang.
International Conference on Learning Representations (ICLR) 2024.
-
Relative Policy-Transition Optimization for Fast Policy Transfer [pdf]
Jiawei Xu, Cheng Zhou, Yizheng Zhang, Baoxiang Wang, Lei Han.
AAAI Conference on Artificial Intelligence (AAAI) 2024.
-
Information Design in Multi-Agent Reinforcement Learning [pdf] [talk]
Yue Lin, Wenhao Li, Hongyuan Zha, Baoxiang Wang.
Advances in Neural Information Processing Systems (NeurIPS) 2023.
-
Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback [pdf]
Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Xuezhou Zhang, Shuai Li.
Advances in Neural Information Processing Systems (NeurIPS) 2023.
-
Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning [pdf]
Jiahui Li, Kun Kuang, Baoxiang Wang, Xingchen Li, Long Chen, Fei Wu, Jun Xiao.
Advances in Neural Information Processing Systems (NeurIPS) 2023.
-
DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning [pdf]
Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li.
International Joint Conference on Artificial Intelligence (IJCAI) 2023.
-
Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition [pdf]
Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Shuai Li.
International Conference on Learning Representations (ICLR) 2023.
-
Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation [pdf]
Jing Dong, Li Shen, Yinggan Xu, Baoxiang Wang.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023 (extended abstract).
-
Diverse Policy Optimization for Structured Action Space [pdf]
Wenhao Li, Baoxiang Wang, Shanchao Yang and Hongyuan Zha.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023.
-
Online Influence Maximization under Decreasing Cascade Model [pdf]
Fang Kong, Jize Xie, Baoxiang Wang, Tao Yao and Shuai Li.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023.
-
Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning [pdf]
Qi Tian, Kun Kuang, Furui Liu, Baoxiang Wang.
AAAI Conference on Artificial Intelligence (AAAI) 2023.
-
Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization [pdf]
Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li.
International Conference on Web Search and Data Mining (WSDM) 2023.
-
Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning [pdf]
Jiahui Li, Kun Kuang, Baoxiang Wang, Furui Liu, Long Chen, Changjie Fan, Fei Wu, Jun Xiao
International Conference on Machine Learning (ICML) 2022.
-
Cascading Bandit under Differential Privacy [pdf]
Kun Wang, Jing Dong, Baoxiang Wang, Shuai Li.
International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2022.
-
Combinatorial Bandits under Strategic Manipulations [pdf]
Jing Dong, Ke Li, Shuai Li, Baoxiang Wang
International Conference on Web Search and Data Mining (WSDM) 2022.
-
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning [pdf]
Jiahui Li, Kun Kuang, Baoxiang Wang, Furui Liu, Long Chen, Fei Wu, Jun Xiao
Conference on Knowledge Discovery and Data Mining (KDD) 2021.
-
The Gambler's Problem and Beyond [pdf]
Baoxiang Wang, Shuai Li, Jiajin Li, Siu On Chan
International Conference on Learning Representations (ICLR) 2020.
-
Learning and Testing Variable Partitions [pdf]
with Andrej Bogdanov
Innovations in Theoretical Computer Science (ITCS) 2020.
-
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces [pdf][code][blog]
Baoxiang Wang, Nidhi Hegde
Advances in Neural Information Processing Systems (NeurIPS) 2019.
-
Recurrent Existence Determination Through Policy Optimization [pdf]
International Joint Conference on Artificial Intelligence (IJCAI) 2019.
-
Metatrace Actor-Critic: Online Step-Size Tuning by Meta-Gradient Descent for Reinforcement Learning Control [pdf]
Kenny Young, Baoxiang Wang, Matthew E. Taylor
International Joint Conference on Artificial Intelligence (IJCAI) 2019.
-
Beyond Winning and Losing: Modeling Human Motivations and Behaviors Using Inverse Reinforcement Learning [pdf][code]
Baoxiang Wang, Tongfang Sun, Xianjun Sam Zheng
AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AAAI-AIIDE) 2019. -
Policy Optimization with Second-Order Advantage Information [pdf][code]
with Jiajin Li
International Joint Conference on Artificial Intelligence (IJCAI) 2018.
-
Contextual Combinatorial Cascading Bandits [pdf][code]
Shuai Li, Baoxiang Wang, Shengyu Zhang, Wei Chen
International Conference on Machine Learning (ICML) 2016. -
PAID: Prioritizing App Issues for Developers by Tracking User Reviews Over Versions [pdf][code]
Cuiyun Gao, Baoxiang Wang, Pinjia He, Jieming Zhu, Yangfan Zhou, Michael R. Lyu
International Symposium on Software Reliability Engineering (ISSRE) 2015.
Journal papers
-
Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization [pdf]
Fang Kong, Xiangcheng Zhang, Baoxiang Wang, Shuai Li.
Transactions on Machine Learning Research (TMLR) 2023.
-
Learning to Boost Resilience of Complex Networks via Neural Edge Rewiring [pdf][code]
Shanchao Yang, Kaili Ma, Baoxiang Wang, Tianshu Yu, Hongyuan Zha.
Transactions on Machine Learning Research (TMLR) 2023.
-
Algorithms and Theory for Supervised Gradual Domain Adaptation [pdf]
Jing Dong, Shiji Zhou, Baoxiang Wang, Han Zhao.
Transactions on Machine Learning Research (TMLR) 2022.
-
Learning Fair Representations via Distance Correlation Minimization [pdf]
Dandan Guo, Chaojie Wang, Baoxiang Wang, Hongyuan Zha
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2022.