Feature dynamic Bayesian networks
Feature Markov Decision Processes (ΦMDPs) [Hut09] are well-suited for learning agents in general environments. Nevertheless, unstructured (Φ)MDPs are limited to relatively simple environments, Structured MDPs like Dynamic Bayesian Networks (DBNs) are us
|Collections||ANU Research Publications|
|Source:||Advances in Intelligent Systems Research: Proceedings of the 2nd Conference on Artificial General Intelligence (AGI 2009)|
|01_Hutter_Feature_dynamic_Bayesian_2009.pdf||411.76 kB||Adobe PDF||Request a copy|
|02_Hutter_Feature_dynamic_Bayesian_2009.pdf||36.89 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.