Folgen
Cassidy Laidlaw
Cassidy Laidlaw
Bestätigte E-Mail-Adresse bei berkeley.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Capture, learning, and synthesis of 3D speaking styles
D Cudeiro, T Bolkart, C Laidlaw, A Ranjan, MJ Black
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
2862019
Perceptual adversarial robustness: Defense against unseen threat models
C Laidlaw, S Singla, S Feizi
arXiv preprint arXiv:2006.12655, 2020
1842020
The boltzmann policy distribution: Accounting for systematic suboptimality in human models
C Laidlaw, A Dragan
arXiv preprint arXiv:2204.10759, 2022
202022
Playing it safe: Adversarial robustness with an abstain option
C Laidlaw, S Feizi
arXiv preprint arXiv:1911.11253, 2019
182019
Uncertain decisions facilitate better preference learning
C Laidlaw, S Russell
Advances in Neural Information Processing Systems 34, 15070-15083, 2021
12*2021
Bridging rl theory and practice with the effective horizon
C Laidlaw, SJ Russell, A Dragan
Advances in Neural Information Processing Systems 36, 2024
92024
Preventing reward hacking with occupancy measure regularization
C Laidlaw, S Singhal, A Dragan
arXiv preprint arXiv:2403.03185, 2024
62024
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
A Siththaranjan, C Laidlaw, D Hadfield-Menell
arXiv preprint arXiv:2312.08358, 2023
22023
Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping
LH Cooke, H Klyne, E Zhang, C Laidlaw, M Tambe, F Doshi-Velez
arXiv preprint arXiv:2312.09983, 2023
2023
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
C Laidlaw, B Zhu, S Russell, A Dragan
arXiv preprint arXiv:2312.08369, 2023
2023
Functional Adversarial Attacks
C Laidlaw, S Feizi
Neural Information Processing Systems, 2019
2019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11