John Asmuth
John Asmuth
Geverifieerd e-mailadres voor cs.rutgers.edu
Titel
Geciteerd door
Geciteerd door
Jaar
A Bayesian sampling approach to exploration in reinforcement learning
J Asmuth, L Li, ML Littman, A Nouri, D Wingate
arXiv preprint arXiv:1205.2664, 2012
1762012
The first probabilistic track of the international planning competition
HLS Younes, ML Littman, D Weissman, J Asmuth
Journal of Artificial Intelligence Research 24, 851-887, 2005
1682005
Potential-based Shaping in Model-based Reinforcement Learning.
J Asmuth, ML Littman, R Zinkov
AAAI, 604-609, 2008
922008
Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search
J Asmuth, ML Littman
arXiv preprint arXiv:1202.3699, 2012
452012
Approaching Bayes-optimalilty using Monte-Carlo tree search
J Asmuth, ML Littman
Proc. 21st Int. Conf. Automat. Plan. Sched., Freiburg, Germany, 2011
262011
Model-based Bayesian reinforcement learning with generalized priors
JT Asmuth
Rutgers University-Graduate School-New Brunswick, 2013
22013
Pac-mdp reinforcement learning with bayesian priors
J Asmuth, L Li, ML Littman, A Nouri, D Wingate
12009
BFS3 Proof of Optimality
J Asmuth, M Littman
2011
Automating Expectation Maximixation
R Zinkov
RLMario: A New Reinforcement Learning Domain
J Asmuth, C Mansley
Author-Title Index Volume 24, 2005
D Achlioptas, J Asmuth, V Bayer-Zubek, M Beetz, A Botea, P Cimiano, ...
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–11