Reusing Risk-Aware Stochastic Abstract Policies in Robotic Navigation Learning

Autor(es)

da Silva, Valdinei Freire ; Koga, Marcelo Li ; Cozman, Fabio Gagliardi ; Reali Costa, Anna Helena ; Behnke, S ; Veloso, M ; Visser, A ; Xiong, R

• Tipo de documento: Artigo Científico
• Fonte: ROBOCUP 2013: ROBOT WORLD CUP XVII; v. 8371, p. 12-pg., 2014-01-01.

Resumo

In this paper we improve learning performance of a risk-aware robot facing navigation tasks by employing transfer learning; that is, we use information from a previously solved task to accelerate learning in a new task. To do so, we transfer risk-aware memoryless stochastic abstract policies into a new task. We show how to incorporate risk-awareness into robotic navigation tasks, in particular when tasks are modeled as stochastic shortest path problems. We then show how to use a modified policy iteration algorithm, called AbsProb-PI, to obtain risk-neutral and risk-prone memoryless stochastic abstract policies. Finally, we propose a method that combines abstract policies, and show how to use the combined policy in a new navigation task. Experiments validate our proposals and show that one can find effective abstract policies that can improve robot behavior in navigation problems. (AU)

• Processo FAPESP: 11/19280-8 - CogBot: integrando informação perceptual e conhecimento semântico na robótica cognitiva
• Beneficiário: Anna Helena Reali Costa
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 12/02190-9 - Transferência de Conhecimento entre Tarefas no Aprendizado por Reforço
• Beneficiário: Marcelo Li Koga
• Modalidade de apoio: Bolsas no Brasil - Mestrado