%0 Journal Article
%T Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states
%A Silva
%A Valdinei Freire da
%A Costa
%A Anna Helena Reali
%J Journal of the Brazilian Computer Society
%D 2009
%I Springer
%R 10.1007/BF03194507
%X 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.
%K machine learning
%K reinforcement learning
%K abstraction
%K partial-policy
%K macro-states.
%U http://www.scielo.br/scielo.php?script=sci_abstract&pid=S0104-65002009000300007&lng=en&nrm=iso&tlng=en