| Texto completo | |
| Autor(es): |
Bonini, Rodrigo Cesar
;
Da Silva, Felipe Leno
;
Glatt, Ruben
;
Spina, Edison
;
Reali Costa, Anna Helena
;
IEEE
Número total de Autores: 6
|
| Tipo de documento: | Artigo Científico |
| Fonte: | 2018 7TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS); v. N/A, p. 6-pg., 2018-01-01. |
| Resumo | |
Reinforcement Learning is a successful yet slow technique to train autonomous agents. Option-based solutions can be used to accelerate learning and to transfer learned behaviors across tasks by encapsulating a partial policy. However, commonly these options are specific for a single task, do not take in account similar features between tasks and may not correspond exactly to an optimal behavior when transferred to another task. Therefore, unprincipled transfer might provide bad options to the agent, hampering the learning process. We here propose a way to discover and reuse learned object-oriented options in a probabilistic way in order to enable better actuation choices to the agent in multiple different tasks. Our experimental evaluation show that our proposal is able to learn and successfully reuse options across different tasks. (AU) | |
| Processo FAPESP: | 16/21047-3 - ALIS: Aprendizado Autônomo em Sistemas Inteligentes |
| Beneficiário: | Anna Helena Reali Costa |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |
| Processo FAPESP: | 15/16310-4 - Transferência de Conhecimento no Aprendizado por Reforço em Sistemas Multiagentes |
| Beneficiário: | Felipe Leno da Silva |
| Modalidade de apoio: | Bolsas no Brasil - Doutorado |
| Processo FAPESP: | 18/00344-5 - Reusando soluções de tarefas prévias em aprendizado por reforço multiagente |
| Beneficiário: | Felipe Leno da Silva |
| Modalidade de apoio: | Bolsas no Exterior - Estágio de Pesquisa - Doutorado |