2103 search results - page 49 / 421 » Approximate Learning of Dynamic Models |
COLT
1993
Springer
15 years 6 months ago
1993
Springer
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approxima...
126
click to vote
AAAI
2006
15 years 3 months ago
2006
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...
100
click to vote
ECML
2005
Springer
15 years 7 months ago
2005
Springer
Abstract. Learning to act in an unknown partially observable domain is a difficult variant of the reinforcement learning paradigm. Research in the area has focused on model-free m...
122
click to vote
ICMLC
2005
Springer
15 years 7 months ago
2005
Springer
In this paper we present a new method, time-striding hidden Markov model (TSHMM), to learn from long-term motion for atomic behaviors and the statistical dependencies among them. T...
133
click to vote
AAMAS
2007
Springer
15 years 8 months ago
2007
Springer
Abstract. The application of reinforcement learning algorithms to multiagent domains may cause complex non-convergent dynamics. The replicator dynamics, commonly used in evolutiona...