Object-Oriented Curriculum Generation for Reinforcement Learning

Autor(es)

Da Silva, Felipe Leno ; Reali Costa, Anna Helena ; ACM

• Tipo de documento: Artigo Científico
• Fonte: PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS (AAMAS' 18); v. N/A, p. 9-pg., 2018-01-01.

Resumo

Autonomously learning a complex task takes a very long time for Reinforcement Learning (RL) agents. One way to learn faster is by dividing a complex task into several simple subtasks and organizing them into a Curriculum that guides Transfer Learning (TL) methods to reuse knowledge in a convenient sequence. However, previous works do not take into account the TL method to build specialized Curricula, leaving the burden of a careful subtask selection to a human. We here contribute novel procedures for: (i) dividing the target task into simpler ones under minimal human supervision; (ii) automatically generating Curricula based on object-oriented task descriptions; and (iii) using generated Curricula for reusing knowledge across tasks. Our experiments show that our proposal achieves a better performance using both manually given and generated subtasks when compared to the state-of-the-art technique in two different domains. (AU)

• 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
• 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