779 search results - page 75 / 156 » Reinforcement Using Supervised Learning for Policy Generaliz... |
JMLR
2008
13 years 9 months ago
2008
We argue that when objects are characterized by many attributes, clustering them on the basis of a random subset of these attributes can capture information on the unobserved attr...
MLDM
2009
Springer
14 years 3 months ago
2009
Springer
In two-class score-based problems the combination of scores from an ensemble of experts is generally used to obtain distributions for positive and negative patterns that exhibit a ...
UAI
2008
13 years 10 months ago
2008
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinfor...
SAB
2010
Springer
13 years 7 months ago
2010
Springer
Learning robot-environment interaction with echo state networks (ESNs) is presented in this paper. ESNs are asked to bootstrap a robot’s control policy from human teacher’s dem...
NIPS
2003
13 years 10 months ago
2003
Recent multi-agent extensions of Q-Learning require knowledge of other agents’ payoffs and Q-functions, and assume game-theoretic play at all times by all other agents. This pap...