publications
* denotes equal contribution, † denotes alphabetical order.
2025
- ICLR 2025Do LLM Agents Have Regret? A Case Study in Online Learning and GamesIn The Thirteenth International Conference on Learning Representations, 2025
2024
- NeurIPS 2024Provable Partially Observable Reinforcement Learning with Privileged InformationIn The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
A shorter version also presented at ICML 2024 ARLET workshop. - ICLR 2024Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLIn The Twelfth International Conference on Learning Representations, 2024
A preliminary version is selected at NeurIPS 2022 Trustworthy and Socially Responsible Machine Learning (TSRML) workshop as an outstanding paper - ICLR 2024Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled PerturbationsIn The Twelfth International Conference on Learning Representations, 2024
2023
- ICML 2023Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information SharingIn International Conference on Machine Learning, 2023
Extended version accepted to SIAM Journal on Control and Optimization (SICON) under revision