An Online POMDP Algorithm Used by the PoliceForce Agents in the RoboCupRescue Simulation.
Sébastien PaquetLudovic TobinBrahim Chaib-draaPublished in: RoboCup (2005)
Keyphrases
- learning algorithm
- computational complexity
- preprocessing
- multi agent
- search space
- k means
- simulated annealing
- detection algorithm
- cost function
- simulation model
- multi agent systems
- worst case
- optimization algorithm
- least squares
- online algorithms
- monte carlo
- segmentation algorithm
- online learning
- optimal solution
- similarity measure