156 citations · 246 across the 43 of their papers we have counts for
4 papers · 1 filter
DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition
Yuki Kadokawa, Jonas Frey, Takahiro Miki +2
Preference-based Reinforcement Learning (PbRL) enables policy learning through simple queries comparing trajectories from a single policy. While human responses to these queries ma…
Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration Interface
Kei Takahashi, Hikaru Sasaki, Takamitsu Matsubara
Imitation learning through a demonstration interface is expected to learn policies for robot automation from intuitive human demonstrations. However, due to the differences in huma…
Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies
Shu-yuan Wang, Hikaru Sasaki, Takamitsu Matsubara
Learning control policies for real-world robotic tasks often involve challenges such as multimodality, local discontinuities, and the need for computational efficiency. These chall…
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…