Følg
Laixi Shi
Laixi Shi
Computing & Mathematical Sciences, Caltech
Verifisert e-postadresse på caltech.edu - Startside
Tittel
Sitert av
Sitert av
År
Pessimistic Q-learning for offline reinforcement learning: Towards optimal sample complexity
L Shi, G Li, Y Wei, Y Chen, Y Chi
International Conference on Machine Learning (ICML), 2022, 2022
1132022
Settling the sample complexity of model-based offline reinforcement learning
G Li, L Shi, Y Chen, Y Chi, Y Wei
The Annals of Statistics 52 (1), 233-260, 2024
104*2024
Micro hand gesture recognition system using ultrasonic active sensing
Y Sang, L Shi, Y Liu
IEEE Access 6, 49339-49347, 2018
902018
Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity
L Shi, Y Chi
Journal of Machine Learning Research 25 (200), 1-91, 2024
692024
Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning
G Li, L Shi, Y Chen, Y Chi
Information and Inference: A Journal of the IMA; Short version as NeurIPS …, 2023
672023
The curious price of distributional robustness in reinforcement learning with a generative model
L Shi, G Li, Y Wei, Y Chen, M Geist, Y Chi
Advances in Neural Information Processing Systems 36, 79903-79917, 2023
422023
Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
P Huang, M Xu, J Zhu, L Shi, F Fang, D Zhao
Conference on Neural Information Processing Systems (NeurIPS), 2022, 2022
332022
Manifold gradient descent solves multi-channel sparse blind deconvolution provably and efficiently
L Shi, Y Chi
IEEE Transactions on Information Theory 67 (7), 4784-4811, 2021
322021
Device-free multiple people localization through floor vibration
L Shi, M Mirshekari, J Fagert, Y Chi, HY Noh, P Zhang, S Pan
Proceedings of the 1st ACM International Workshop on Device-Free Human …, 2019
302019
Seeing is not believing: Robust reinforcement learning against spurious correlation
W Ding, L Shi, Y Chi, D Zhao
Advances in Neural Information Processing Systems 36, 66328-66363, 2023
252023
Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
L Shi, E Mazumdar, Y Chi, A Wierman
International Conference on Machine Learning (ICML), 2024, 2024
122024
Sample complexity of offline distributionally robust linear markov decision processes
H Wang, L Shi, Y Chi
arXiv preprint arXiv:2403.12946, 2024
112024
Federated offline reinforcement learning: Collaborative single-policy coverage suffices
J Woo, L Shi, G Joshi, Y Chi
arXiv preprint arXiv:2402.05876, 2024
92024
A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning
Y Wang, M Xu, L Shi, Y Chi
Uncertainty in Artificial Intelligence, 2226-2236, 2023
92023
Offline Reinforcement Learning with On-Policy Q-Function Regularization
L Shi, R Dadashi, Y Chi, PS Castro, M Geist
European Conference on Machine Learning (ECML), 2023, 2023
42023
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
S Gu, L Shi, Y Ding, A Knoll, CJ Spanos, A Wierman, M Jin
Advances in Neural Information Processing Systems 37, 17247-17285, 2025
32025
Zoom Out: Abstractions for Efficient Radar Algorithms on COTS architectures
TM Low, Y Chi, J Hoe, S Kumar, A Prabhakara, L Shi, U Sridhar, ...
2022 IEEE International Symposium on Phased Array Systems & Technology (PAST …, 2022
32022
Tractable Equilibrium Computation in Markov Games through Risk Aversion
E Mazumdar*, K Panaganti*, L Shi*
arXiv preprint arXiv:2406.14156, 2024
22024
Robust Camera Pose Estimation For Image Stitching
L Shi, D Liu, J Thornton
2021 IEEE International Conference on Image Processing (ICIP), 2838-2842, 2021
22021
Fusion-based digital image correlation framework for strain measurement
L Shi, D Liu, M Umeda, N Hana
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
22021
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20