3643 search results - page 177 / 729 » Learning Submodular Functions |
149
click to vote
COLT
2007
Springer
16 years 19 days ago
2007
Springer
Abstract. We consider the problem of learning an acyclic discrete circuit with n wires, fan-in bounded by k and alphabet size s using value injection queries. For the class of tran...
144
click to vote
COLT
1992
Springer
15 years 10 months ago
1992
Springer
Machine learning of limit programs (i.e., programs allowed finitely many mind changes about their legitimate outputs) for computable functions is studied. Learning of iterated lim...
165
click to vote
ECML
2006
Springer
15 years 10 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...
236
click to vote
AAIP
2009
15 years 7 months ago
2009
Inductive programming systems characteristically exhibit an exponential explosion in search time as one increases the size of the programs to be generated. As a way of overcoming ...
182
click to vote
GECCO
2010
Springer
15 years 9 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...