813 search results - page 23 / 163 » Ensemble Algorithms in Reinforcement Learning |
NIPS
1998
13 years 8 months ago
1998
NIPS
1994
13 years 8 months ago
1994
ATAL
2010
Springer
13 years 6 months ago
2010
Springer
CIDM
2009
IEEE
14 years 2 months 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...
EWRL
2008
13 years 9 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...