Folgen
Kunhe Yang
Kunhe Yang
University of California, Berkeley
Bestätigte E-Mail-Adresse bei berkeley.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Q-learning with logarithmic regret
K Yang, L Yang, S Du
International Conference on Artificial Intelligence and Statistics, 1576-1584, 2021
702021
Oracle-efficient online learning for smoothed adversaries
N Haghtalab, Y Han, A Shetty, K Yang
Advances in Neural Information Processing Systems 35, 4072-4084, 2022
35*2022
Optimal conservative offline rl with general function approximation via augmented lagrangian
P Rashidinejad, H Zhu, K Yang, S Russell, J Jiao
arXiv preprint arXiv:2211.00716, 2022
332022
Nudge: Stochastically Improving upon FCFS
I Grosof, K Yang, Z Scully, M Harchol-Balter
Abstract Proceedings of the 2021 ACM SIGMETRICS/International Conference on …, 2021
192021
Calibrated stackelberg games: Learning optimal commitments against calibrated agents
N Haghtalab, C Podimata, K Yang
Advances in Neural Information Processing Systems 36, 2024
152024
Fundamental bounds on online strategic classification
S Ahmadi, A Blum, K Yang
Proceedings of the 24th ACM Conference on Economics and Computation, 22-58, 2023
92023
Computational Aspects of Bayesian Persuasion under Approximate Best Response
K Yang, H Zhang
arXiv preprint arXiv:2402.07426, 2024
42024
Platforms for Efficient and Incentive-Aware Collaboration
N Haghtalab, M Qiao, K Yang
arXiv preprint arXiv:2402.15169, 2024
12024
Is Knowledge Power? On the (Im) possibility of Learning from Strategic Interaction
N Ananthakrishnan, N Haghtalab, C Podimata, K Yang
arXiv preprint arXiv:2408.08272, 2024
2024
Truthfulness of Calibration Measures
N Haghtalab, M Qiao, K Yang, E Zhao
arXiv preprint arXiv:2407.13979, 2024
2024
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
S Ahmadi, K Yang, H Zhang
arXiv preprint arXiv:2407.11619, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11