| Linear stochastic bandits under safety constraints S Amani, M Alizadeh, C Thrampoulidis Advances in Neural Information Processing Systems 32, 2019 | 136 | 2019 |
| Safe linear thompson sampling with side information A Moradipari, S Amani, M Alizadeh, C Thrampoulidis IEEE Transactions on Signal Processing 69, 3755-3767, 2021 | 67* | 2021 |
| Safe Reinforcement Learning with Linear Function Approximation S Amani, C Thrampoulidis, LF Yang International Conference on Machine Learning, 243-253, 2021 | 47 | 2021 |
| Regret bound for safe gaussian process bandit optimization S Amani, M Alizadeh, C Thrampoulidis Learning for Dynamics and Control, 158-159, 2020 | 24 | 2020 |
| Ucb-based algorithms for multinomial logistic regression bandits S Amani, C Thrampoulidis Advances in Neural Information Processing Systems 34, 2913-2924, 2021 | 15 | 2021 |
| Decentralized Multi-Agent Linear Bandits with Safety Constraints S Amani, C Thrampoulidis Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6627-6635, 2021 | 13 | 2021 |
| Generalized linear bandits with safety constraints S Amani, M Alizadeh, C Thrampoulidis ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 13 | 2020 |
| Distributed contextual linear bandits with minimax optimal communication cost S Amani, T Lattimore, A György, L Yang International Conference on Machine Learning, 691-717, 2023 | 9 | 2023 |
| Provably Efficient Lifelong Reinforcement Learning with Linear Representation S Amani, L Yang, CA Cheng The Eleventh International Conference on Learning Representations, 2023 | 6* | 2023 |
| Doubly pessimistic algorithms for strictly safe off-policy optimization S Amani, LF Yang 2022 56th Annual Conference on Information Sciences and Systems (CISS), 113-118, 2022 | 6 | 2022 |
| Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning Y Wang, C Liu, Y Li, S Amani, B Zhou, LF Yang arXiv preprint arXiv:2412.03767, 2024 | | 2024 |
| Learning in Safety-critical, Lifelong, and Multi-agent Systems: Bandits and RL Approaches S Amani Geshnigani UCLA, 2023 | | 2023 |
| A generalization of weighted sparse decomposition to negative weights G Delfi, S Aziznejad, S Amani, M Babaie-Zadeh, C Jutten 2017 25th European Signal Processing Conference (EUSIPCO), 2146-2150, 2017 | | 2017 |
| DEXR: A Unified Approach Towards Environment Agnostic Exploration Y Wang, Y Li, S Amani, L Yang | | |
Christos ThrampoulidisAssistant Professor, University of British Columbia, ECE DepartmentPotvrđena adresa e-pošte na ucsb.edu