dc.creator | SILVA, Valdinei Freire da | |
dc.creator | COSTA, Anna Helena Reali | |
dc.date.accessioned | 2012-03-25T23:05:48Z | |
dc.date.accessioned | 2018-07-04T13:48:07Z | |
dc.date.available | 2012-03-25T23:05:48Z | |
dc.date.available | 2018-07-04T13:48:07Z | |
dc.date.created | 2012-03-25T23:05:48Z | |
dc.date.issued | 2009 | |
dc.identifier | Journal of the Brazilian Computer Society, v.15, n.3, p.65-75, 2009 | |
dc.identifier | 0104-6500 | |
dc.identifier | http://producao.usp.br/handle/BDPI/2752 | |
dc.identifier | 10.1590/S0104-65002009000300007 | |
dc.identifier | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002009000300007 | |
dc.identifier | http://www.scielo.br/pdf/jbcos/v15n3/v15n3a07.pdf | |
dc.identifier.uri | http://repositorioslatinoamericanos.uchile.cl/handle/2250/1601924 | |
dc.description.abstract | 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. | |
dc.language | eng | |
dc.publisher | Sociedade Brasileira de Computação | |
dc.relation | Journal of the Brazilian Computer Society | |
dc.rights | Copyright Sociedade Brasileira de Computação | |
dc.rights | openAccess | |
dc.subject | Machine learning | |
dc.subject | Reinforcement learning | |
dc.subject | Abstraction | |
dc.subject | Partial-policy | |
dc.subject | Macro-states | |
dc.title | Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states | |
dc.type | Artículos de revistas | |