Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations
Simon Holk, Ryosuke Takanami, Tatsuya Matsushima +4
Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behaviorally correct but paired with…
cs.RO2025
FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions
Daniel Marta, Simon Holk, Miguel Vasco +6
Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user prefere…