Bianchi R.A.C.Celiberto L.A.Santos P.E.Matsuura J.P.Lopez De Mantaras R.2019-08-192019-08-192015BIANCHI, REINALDO A.C.; JUNIOR, LUIZ A. CELIBERTO; Santos, Paulo E.; MATSUURA, JACKSON P.; LÓPEZ DE MÀNTARAS, RAMÓN. Transferring knowledge as heuristics in reinforcement learning: a case-based approach. Artificial Intelligence (General Ed.), v. 226, p. 102-121, 2015.0004-3702https://repositorio.fei.edu.br/handle/FEI/1217© 2015 Elsevier B.V.Abstract The goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure in one domain (the target) that are obtained from another (simpler) domain (the source domain). This meta-algorithm works in three stages: first, it uses a Reinforcement Learning step to learn a task on the source domain, storing the knowledge thus obtained in a case base; second, it does an unsupervised mapping of the source-domain actions to the target-domain actions; and, third, the case base obtained in the first stage is used as heuristics to speed up the learning process in the target domain. A set of empirical evaluations were conducted in two target domains: the 3D mountain car (using a learned case base from a 2D simulation) and stability learning for a humanoid robot in the Robocup 3D Soccer Simulator (that uses knowledge learned from the Acrobot domain). The results attest that our transfer learning algorithm outperforms recent heuristically-accelerated reinforcement learning and transfer learning algorithms.Acesso AbertoArtigo10.1016/j.artint.2015.05.008Case-based reasoningReinforcement learningTransfer learning