334 search results - page 47 / 67 » How to Dynamically Merge Markov Decision Processes |
AAAI
2006
14 years 11 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
GECCO
2005
Springer
15 years 3 months ago
2005
Springer
Recent adaptive image interpretation systems can reach optimal performance for a given domain via machine learning, without human intervention. The policies are learned over an ex...
WISE
2002
Springer
15 years 2 months ago
2002
Springer
A distributed search system consists of a large number of autonomous search servers logically connected in a peerto-peer network. Each search server maintains a local index of a c...
ATAL
2004
Springer
15 years 3 months ago
2004
Springer
Single-agent reinforcement learners in time-extended domains and multi-agent systems share a common dilemma known as the credit assignment problem. Multi-agent systems have the st...
RTSS
2003
IEEE
15 years 2 months ago
2003
IEEE
Often, data used in on-line decision making (for example, in determining how to react to changes in process behavior, traffic flow control, etc.) is dynamic in nature and hence ...