Using Generalized Learning Automata for State Space Aggregation in MAS.
Yann-Michaël De HauwerePeter VrancxAnn NowéPublished in: KES (1) (2008)
Keyphrases
- learning automata
- state space
- reinforcement learning
- multi agent systems
- pursuit algorithm
- learning automaton
- genetic algorithm
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- multi agent
- machine learning
- multiagent systems
- heuristic search
- cooperative
- state variables
- dynamic programming
- particle filter
- learning algorithm
- basis functions
- dynamical systems
- agent technology
- planning problems
- stochastic domains
- goal state
- unsupervised learning