Title | ||
---|---|---|
Transferring knowledge as heuristics in reinforcement learning: A case-based approach |
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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1016/j.artint.2015.05.008 | Artificial Intelligence |
Keywords | DocType | Volume |
Case-based reasoning,Reinforcement learning,Transfer learning | Journal | 226 |
Issue | ISSN | Citations |
1 | 0004-3702 | 5 |
PageRank | References | Authors |
0.41 | 42 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reinaldo A. C. Bianchi | 1 | 147 | 17.63 |
Luiz A. Celiberto, Jr. | 2 | 18 | 2.32 |
Paulo E. Santos | 3 | 131 | 20.29 |
Jackson Paul Matsuura | 4 | 8 | 1.56 |
Ramon Lopez de Mantaras | 5 | 706 | 52.40 |