Stebėti
Bryan Chan
Pavadinimas
Cituota
Cituota
Metai
Learning from guided play: Improving exploration for adversarial imitation learning with simple auxiliary tasks
T Ablett, B Chan, J Kelly
IEEE Robotics and Automation Letters 8 (3), 1263-1270, 2023
112023
Heteroscedastic uncertainty for robust generative latent dynamics
O Limoyo, B Chan, F Marić, B Wagstaff, AR Mahmood, J Kelly
IEEE Robotics and Automation Letters 5 (4), 6654-6661, 2020
82020
RL Sandbox
B Chan
https://github.com/chanb/rl_sandbox_public, 2020
52020
Learning from guided play: A scheduled hierarchical approach for improving exploration in adversarial imitation learning
T Ablett*, B Chan*, J Kelly
NeurIPS 2021 Deep Reinforcement Learning Workshop, 2021
42021
Toward Understanding In-context vs. In-weight Learning
B Chan*, X Chen*, A György, D Schuurmans
arXiv preprint arXiv:2410.23042, 2024
12024
Value-penalized auxiliary control from examples for learning without rewards or demonstrations
T Ablett, B Chan, J Haoran Wang, J Kelly
CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data, 2024
12024
Mitigating the curse of horizon in Monte-Carlo returns
A Ayoub*, D Szepesvari*, F Zanini*, B Chan*, D Gupta, BC da Silva, ...
Reinforcement Learning Conference, 2024
12024
A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning
B Chan, K Pereida, J Bergstra
NeurIPS 2023 Workshop on Robot Learning, 2023
12023
Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations
B Chan, A Leung, J Bergstra
CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data, 2024
2024
Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.
Straipsniai 1–9