|
postdoctoral researcher |
|
Gergely Neu |
|
Gergely Neu, Csaba Szepesvári |
|
Publications |
|
Apprenticeship learning using inverse reinforcement learning and gradient methods |
|
Training parsers by inverse reinforcement learning |
|
Contact info: |
|
Phone: +36 70 271 3988 Email: gergely.neu@gmail.com |
|
The online loop-free stochastic shortest path problem |
|
Gergely Neu, András György, Csaba Szepesvári, András Antos |
|
Online Markov decision processes under bandit feedback |
|
Near-optimal rates for limited-delay universal lossy source coding |
|
The adversarial stochastic shortest path problem with unknown transition probabilities |
|
Prediction by random-walk perturbation |
|
An efficient algorithm for learning with semi-bandit information |
|
Alexander Zimin, Gergely Neu |
|
Online learning in Markov decision processes by Relative Entropy Policy Search |
