2 papers
cs.LG2026
ConceptACT: Episode-Level Concepts for Sample-Efficient Robotic Imitation Learning
Jakob Karalus, Friedhelm Schwenker
Imitation learning enables robots to acquire complex manipulation skills from human demonstrations, but current methods rely solely on low-level sensorimotor data while ignoring th…
cs.AI2024
Tell me why: Training preferences-based RL with human preferences and step-level explanations
Jakob Karalus
Human-in-the-loop reinforcement learning allows the training of agents through various interfaces, even for non-expert humans. Recently, preference-based methods (PbRL), where the…