no code implementations • 22 Jan 2024 • Yao Lu, Hiram Rayo Torres Rodriguez, Sebastian Vogel, Nick van de Waterlaat, Pavol Jancura
Since models are typically quantized for edge deployment, recent work has investigated quantization-aware NAS (QA-NAS) to search for highly accurate and efficient quantized models.
no code implementations • 4 Apr 2023 • Ariyan Bighashdel, Daan de Geus, Pavol Jancura, Gijs Dubbelman
Learning anticipation in Multi-Agent Reinforcement Learning (MARL) is a reasoning paradigm where agents anticipate the learning steps of other agents to improve cooperation among themselves.
1 code implementation • 14 Jul 2021 • Ariyan Bighashdel, Panagiotis Meletis, Pavol Jancura, Gijs Dubbelman
This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn an a priori unknown number of nonlinear reward functions from unlabeled experts' demonstrations.