activity
20172025
most citedOn-device Online Learning and Semantic Management of TinyML Systems

17 citations · 67 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2024

TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning

Batıkan Bora Ormancı, Phillip Swazinna, Steffen Udluft +1

In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dyna…

cs.LG2024★ 17 cited

On-device Online Learning and Semantic Management of TinyML Systems

Haoyu Ren, Xue Li, Darko Anicic +1

Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of…

cs.LG2023★ 2 cited

TinyMetaFed: Efficient Federated Meta-Learning for TinyML

Haoyu Ren, Xue Li, Darko Anicic +1

The field of Tiny Machine Learning (TinyML) has made substantial advancements in democratizing machine learning on low-footprint devices, such as microcontrollers. The prevalence o…

cs.LG2023

Automatic Trade-off Adaptation in Offline RL

Phillip Swazinna, Steffen Udluft, Thomas Runkler

Recently, offline RL algorithms have been proposed that remain adaptive at runtime. For example, the LION algorithm \cite{lion} provides the user with an interface to set the trade…

cs.LG2023

TinyReptile: TinyML with Federated Meta-Learning

Haoyu Ren, Darko Anicic, Thomas A. Runkler

Tiny machine learning (TinyML) is a rapidly growing field aiming to democratize machine learning (ML) for resource-constrained microcontrollers (MCUs). Given the pervasiveness of t…

cs.LG2022★ 1 cited

Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning

Phillip Swazinna, Steffen Udluft, Daniel Hein +1

Offline reinforcement learning (RL) Algorithms are often designed with environments such as MuJoCo in mind, in which the planning horizon is extremely long and no noise exists. We…