Speeding-up reinforcement learning through abstraction and transfer learning

Marcelo Li Koga, Valdinei Freire Da Silva, Fabio Gagliardi Cozman, Anna Helena Reali Costa

Resultado de la investigación: Contribución a una conferenciaArtículo de conferencia

11 Citas (Scopus)

Resumen

We are interested in the following general question: is it possible to abstract knowledge that is generated while learning the solution of a problem, so that this abstraction can accelerate the learning process? Moreover, is it possible to transfer and reuse the acquired abstract knowledge to accelerate the learning process for future similar tasks? We propose a framework for conducting simultaneously two levels of reinforcement learning, where an abstract policy is learned while learning of a concrete policy for the problem, such that both policies are refined through exploration and interaction of the agent with the environment. We explore abstraction both to accelerate the learning process for an optimal concrete policy for the current problem, and to allow the application of the generated abstract policy in learning solutions for new problems. We report experiments in a robot navigation environment that show our framework to be effective in speeding up policy construction for practical problems and in generating abstractions that can be used to accelerate learning in new similar problems. Copyright © 2013, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Idioma originalInglés estadounidense
Páginas119-126
Número de páginas8
EstadoPublicada - 1 ene 2013
Publicado de forma externa
Evento12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013 -
Duración: 1 ene 2013 → …

Conferencia

Conferencia12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013
Período1/01/13 → …

Huella Profundice en los temas de investigación de 'Speeding-up reinforcement learning through abstraction and transfer learning'. En conjunto forman una huella única.

  • Citar esto

    Koga, M. L., Da Silva, V. F., Cozman, F. G., & Costa, A. H. R. (2013). Speeding-up reinforcement learning through abstraction and transfer learning. 119-126. Papel presentado en 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, .