|
CONTINUOUS ACTION REINFORCEMENT LEARNING AUTOMATA. Performance and convergence Host Publication: 3rd International Conference on Agents and Artificial Intelligence ICAART 2011 Authors: A. Rodriguez, R. Grau and A. Nowé Publication Year: 2011 Number of Pages: 6
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.
|
