SciELO - Scientific Electronic Library Online

 
vol.15 issue3An improved particle filter for sparse environments author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

Share


Journal of the Brazilian Computer Society

Print version ISSN 0104-6500On-line version ISSN 1678-4804

Abstract

SILVA, Valdinei Freire da  and  COSTA, Anna Helena Reali. Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states. J. Braz. Comp. Soc. [online]. 2009, vol.15, n.3, pp.65-75. ISSN 0104-6500.  http://dx.doi.org/10.1007/BF03194507.

Reinforcement Learning is carried out on-line, through trial-and-error interactions of the agent with the environment, which can be very time consuming when considering robots. In this paper we contribute a new learning algorithm, CFQ-Learning, which uses macro-states, a low-resolution discretisation of the state space, and a partial-policy to get around obstacles, both of them based on the complexity of the environment structure. The use of macro-states avoids convergence of algorithms, but can accelerate the learning process. In the other hand, partial-policies can guarantee that an agent fulfils its task, even through macro-state. Experiments show that the CFQ-Learning performs a good balance between policy quality and learning rate.

Keywords : machine learning; reinforcement learning; abstraction; partial-policy; macro-states.

        · text in English     · English ( pdf epdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License