Monte-Carlo Swarm Policy Search

Jérémy Fix (1) , Matthieu Geist (1)

1 IMS : Information, Multimodalité & Signal

Finding optimal controllers of stochastic systems is a particularly challenging problem tackled by the optimal control and reinforcement learning communities. A classic paradigm for handling such problems is provided by Markov Decision Processes. However, the resulting underlying optimization problem is difficult to solve. In this paper, we explore the possible use of Particle Swarm Optimization to learn optimal controllers and show through some non-trivial experiments that it is a particularly promising lead.

Mots clés: particle swarm optimization; optimal control; policy search

Domaines: Machine Learning [stat.ML]

Jérémy Fix, Matthieu Geist. Monte-Carlo Swarm Policy Search. Symposium on Swarm Intelligence and Differential Evolution, Apr 2012, Zakopane, Poland. pp.75-83, ⟨10.1007/978-3-642-29353-5_9⟩. ⟨hal-00695540⟩