813 search results - page 23 / 163 » Ensemble Algorithms in Reinforcement Learning |
ATAL
2010
Springer
15 years 4 months ago
2010
Springer
166
click to vote
CIDM
2009
IEEE
16 years 20 days ago
2009
IEEE
— Both theory and a wealth of empirical studies have established that ensembles are more accurate than single predictive models. Unfortunately, the problem of how to maximize ens...
169
click to vote
EWRL
2008
15 years 7 months ago
2008
Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level a...