BDBComp
Parceria:
SBC
Accelerating reinforcement learning by reusing abstract policies

Yannick Plaino BergamoTiago MatosValdinei Freire da SilvaAnna Helena Reali Costa

Reinforcement learning (RL) provides a general approach for devel- oping intelligent agents that are able to optimize their behaviors in stochastic environments. Unfortunately, most work in RL is based on propositional rep- resentations, making it difficult to apply it to more complex real-world tasks in which states and actions are more naturally represented in relational form. Moreover, most work in RL does not take into account existing solutions to sim- ilar problems when learning a policy to solve a new problem, and consequently solves the new problem from scratch, what can be very time consuming. In this article we explore the powerful possibilities of using relational descriptions so that we can learn abstract policies, and in reusing these policies to improve initial performance of an RL learner in a similar new problem. Experiments carried out attest the effectiveness of our proposal.

http://www.lbd.dcc.ufmg.br/colecoes/enia/2011/0031.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD