Authors:
Abdel Rodríguez
1
;
Ricardo Grau
2
and
Ann Nowé
3
Affiliations:
1
Central University of Las Villas and Vrije Universiteit Brussel, Cuba
;
2
Central University of Las Villas, Cuba
;
3
Vrije Universiteit Brussel, Belgium
Keyword(s):
CARLA, Convergence, Performance.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Autonomous Systems
;
Distributed and Mobile Software Systems
;
Enterprise Information Systems
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Multi-Agent Systems
;
Software Engineering
;
Symbolic Systems
Abstract:
Reinforcement Learning is a powerful technique for agents to solve unknown Markovian Decision Processes, from the possibly delayed signals that they receive. Most RL work, in particular for multi-agent settings, assume a discrete action set. Learning automata are reinforcement learners, belonging to the category of policy iterators, that exhibit nice convergence properties in discrete action settings. Unfortunately, most applications assume continuous actions. A formulation for a continuous action reinforcement learning automaton already exists, but there is no convergence guarantee to optimal decisions. An improve of the performance of the method is proposed in this paper as well as the proof for the local convergence.