Alignment in Vision-Oriented Syntactic Language Games for Teams of Robots Using Stochastic Regular Grammars and Reinforcement Learning
This paper approaches the syntactic alignment of a robot team by means of dialogic language games by applying online probabilistic reinforcement learning algorithms. The main contribution of the paper is the application of stochastic regular grammars, with learning capability, to generate the robots’ language. First, the paper describes the syntactic language games, in particular the type of grammar and syntactic rules of the robots’ language and the dynamic process of the language games which are based on dialogic communicative acts and a reinforcement learning policy that allows the robot team to converge to a common language. Afterwards, the experimental results are presented and discussed. The experimental work has been organized around the linguistic description of visual scenes of the blocks world type.
KeywordsStochastic Grammars Reinforcement Learning Dynamics of Artificial Languages Language Games Multi-robot Systems Self-Collective Coordination and Computational Semiotics
Unable to display preview. Download preview PDF.
- 1.Steels, L. (ed.): Experiments in Cultural Language Evolution. John Benjamins (2012)Google Scholar
- 2.Maravall, D., de Lope, J., Domínguez, R.: Coordination of Communication in Robot Teams by Reinforcement Learning. Robotics and Autonomous Systems (2012) (in press), doi:10.1016/j. robot 201207007Google Scholar
- 3.Marconi, D.: Lexical Competence. MIT Press (1997)Google Scholar