2 papers
cs.RO2025
Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications
Wataru Hatanaka, Ryota Yamashina, Takamitsu Matsubara
Symbolic task representation is a powerful tool for encoding human instructions and domain knowledge. Such instructions guide robots to accomplish diverse objectives and meet const…
cs.RO2023
Reinforcement Learning of Action and Query Policies with LTL Instructions under Uncertain Event Detector
Wataru Hatanaka, Ryota Yamashina, Takamitsu Matsubara
Reinforcement learning (RL) with linear temporal logic (LTL) objectives can allow robots to carry out symbolic event plans in unknown environments. Most existing methods assume tha…