Prati
Matin Aghaei
Matin Aghaei
Simon Fraser University
Potvrđena adresa e-pošte na sfu.ca - Početna stranica
Naslov
Citirano
Citirano
Godina
Towards principled, practical policy gradient for bandits and tabular mdps
M Lu, M Aghaei, A Raj, S Vaswani
arXiv preprint arXiv:2405.13136, 2024
32024
Practical principled policy optimization for finite MDPs
M Lu, M Aghaei, A Raj, S Vaswani
OPT 2023: Optimization for Machine Learning, 2023
12023
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–2