2073 search results - page 173 / 415 » Learning for Dynamic Subsumption |
116
click to vote
ICPR
2000
IEEE
15 years 7 months ago
2000
IEEE
Many realistic visual recognition tasks are “open” in the sense that the number and nature of the categories to be learned are not initially known, and there is no closed set ...
102
click to vote
MHVR
1994
15 years 7 months ago
1994
We are collaboratively designing "ScienceSpace," a collection of virtual worlds designed to explore the potential utility of physical immersion and multisensory perceptio...
161
click to vote
ECML
2007
Springer
15 years 7 months ago
2007
Springer
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
109
click to vote
FLAIRS
1998
15 years 4 months ago
1998
Manyindustrial processes involve makingparts with an assemblyof machines, where each machinecarries out an operation on a part, and the finished product requires a wholeseries of ...
114
click to vote
AAAI
1996
15 years 4 months ago
1996
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...