Следене
Paniz Behboudian
Paniz Behboudian
Data Scientist, Granify
Потвърден имейл адрес: granify.com
Заглавие
Позовавания
Позовавания
Година
Useful policy invariant shaping from arbitrary advice
P Behboudian, Y Satsangi, ME Taylor, A Harutyunyan, M Bowling
arXiv preprint arXiv:2011.01297, 2020
102020
Policy invariant explicit shaping: an efficient alternative to reward shaping
P Behboudian, Y Satsangi, ME Taylor, A Harutyunyan, M Bowling
Neural Computing and Applications, 1-14, 2022
62022
Bandit-Based Policy Invariant Explicit Shaping for Incorporating External Advice in Reinforcement Learning
Y Satsangi, P Behboudian
arXiv preprint arXiv:2304.07163, 2023
2023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–3