Applying topological maps to accelerate reinforcement learning in mobile robot navigation

Abstract

Abstracr This article proposes a procedure to accelerate reinforcement learning in the task of mobile robot navigation using a latent-like learning schema. This concept considers that part of a task can be learned before the agent receives some indication of how to perform such a task A simple mechanism permits that the proposed Topological Reinforcement… (More)

5 Figures and Tables

Cite this paper

@article{Braga2002ApplyingTM, title={Applying topological maps to accelerate reinforcement learning in mobile robot navigation}, author={A.P.S. Braga and A.F.R. Araiijo}, journal={IEEE International Conference on Systems, Man and Cybernetics}, year={2002}, volume={2}, pages={7-12} }