| Neural trust region/proximal policy optimization attains globally optimal policy B Liu, Q Cai, Z Yang, Z Wang Advances in neural information processing systems 32, 2019 | 207 | 2019 |
| Reason for future, act for now: A principled framework for autonomous llm agents with provable sample efficiency Z Liu, H Hu, S Zhang, H Guo, S Ke, B Liu, Z Wang arXiv preprint arXiv:2309.17382, 2023 | 21* | 2023 |
| Off-policy evaluation and learning from logged bandit feedback: Error reduction via surrogate policy Y Xie, B Liu, Q Liu, Z Wang, Y Zhou, J Peng International Conference on Learning Representations, 2018 | 20 | 2018 |
| Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence B Liu, J Li, Z Yang, HT Wai, M Hong, Y Nie, Z Wang Advances in Neural Information Processing Systems, 2022 | 15* | 2022 |
| Differentiable bilevel programming for stackelberg congestion games J Li, J Yu, Q Wang, B Liu, Z Wang, YM Nie arXiv preprint arXiv:2209.07618, 2022 | 13 | 2022 |
| Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL F Zhang, B Liu, K Wang, VYF Tan, Z Yang, Z Wang Advances in Neural Information Processing Systems, 2022 | 8 | 2022 |
| An analysis of attention via the lens of exchangeability and latent variable models Y Zhang, B Liu, Q Cai, L Wang, Z Wang arXiv preprint arXiv:2212.14852, 2022 | 7 | 2022 |
| Let models speak ciphers: Multiagent debate through embeddings C Pham, B Liu, Y Yang, Z Chen, T Liu, J Yuan, BA Plummer, Z Wang, ... arXiv preprint arXiv:2310.06272, 2023 | 5 | 2023 |
| Policy Optimization in Zero-Sum Markov Games: Fictitious Self-Play Provably Attains Nash Equilibria B Liu, Z Yang, Z Wang | 3 | 2020 |
| Provably mitigating overoptimization in rlhf: Your sft loss is implicitly an adversarial regularizer Z Liu, M Lu, S Zhang, B Liu, H Guo, Y Yang, J Blanchet, Z Wang arXiv preprint arXiv:2405.16436, 2024 | 2 | 2024 |
| Model-based reparameterization policy gradient methods: Theory and practical algorithms S Zhang, B Liu, Z Wang, T Zhao Advances in Neural Information Processing Systems 36, 2024 | 2 | 2024 |
| Achieving hierarchy-free approximation for bilevel programs with equilibrium constraints J Li, J Yu, B Liu, Y Nie, Z Wang International Conference on Machine Learning, 20312-20335, 2023 | 2 | 2023 |
| Differentiable Arbitrating in Zero-sum Markov Games J Wang, M Song, F Gao, B Liu, Z Wang, Y Wu International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023 | 1 | 2023 |
| -Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model Y Zhang, L Chen, B Liu, Y Yang, Q Cui, Y Tao, H Yang arXiv preprint arXiv:2403.07191, 2024 | | 2024 |
| Double duality: variational primal-dual policy optimization for constrained reinforcement learning Z Li, B Liu, Z Yang, Z Wang, M Wang Journal of Machine Learning Research 24 (385), 1-43, 2023 | | 2023 |
| BooVI: provably efficient bootstrapped value iteration B Liu, Q Cai, Z Yang, Z Wang Advances in Neural Information Processing Systems 34, 7041-7053, 2021 | | 2021 |
Zhaoran WangAssistant Professor at Northwestern University在 northwestern.edu 的电子邮件经过验证
