A hybrid approach based on multi-agent geosimulation and reinforcement learning to solve a UAV patrolling problem.
Jimmy PerronJimmy HoganBernard MoulinJean BergerMicheline BélangerPublished in: WSC (2008)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- multi agent systems
- intelligent agents
- multi agent reinforcement learning
- autonomous agents
- single agent
- multi agent environments
- function approximation
- state space
- multiagent systems
- markov decision processes
- learning algorithm
- optimal policy
- agent oriented
- vision based navigation
- decision problems
- agent based simulations
- heterogeneous agents
- partially observable markov decision processes
- information gathering
- coalition formation
- decision making