526 search results - page 16 / 106 » Efficient Algorithms for Online Decision Problems |
COLT
2008
Springer
13 years 11 months ago
2008
Springer
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
EDBT
2008
ACM
14 years 9 months ago
2008
ACM
The top-k retrieval problem requires finding k objects most similar to a given query object. Similarities between objects are most often computed as aggregated similarities of the...
SODA
1998
ACM
13 years 10 months ago
1998
ACM
We present the first polylog-competitive online algorithm for the general multicast admission control and routing problem in the throughput model. The ratio of the number of reque...
ICRA
2003
IEEE
14 years 2 months ago
2003
IEEE
— Mapping an environment with an imaging sensor becomes very challenging if the environment to be mapped is unknown and has to be explored. Exploration involves the planning of v...
ATAL
2009
Springer
14 years 3 months ago
2009
Springer
One of the key problems in reinforcement learning is balancing exploration and exploitation. Another is learning and acting in large or even continuous Markov decision processes (...