Abstract concepts pose a fundamental challenge for multimodal interactive systems, as they cannot be grounded in single perceptual features or fixed motor patterns; instead, they require abstraction across perception, action, language, and affect. Examples include superordinate categories (e.g., animal, tool), generali...
Progress-Heuristicized Inverse Reinforcement Learning (PHIRL), a data-efficient framework that learns robust reward functions by jointly leveraging demonstrations and feedback, uses progress, a feedback modality that describes cumulative task completion.
Hang Yu, James Staley, Cheng-Xi Tsou et al.· 0 citations
Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise stud...
Theodor Wulff, Sergio Lanza, Tamara Bíla et al.· 0 citations
This work develops LEMUR: Learning to Align with Multi-Objective Reinforcement Learning with Preference feedback, a novel framework where an agent interactively learns from the preferences of multiple humans to learn optimal multi-objective policies.
Manith Adikari, Bei Peng, Samuele Vinanzi et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
