Optimizing expensive-to-evaluate black-box functions of discrete (and potentially continuous) design parameters is a ubiquitous problem in scientific and engineering …
The fields of both Natural Language Processing (NLP) and Automated Machine Learning (AutoML) have achieved remarkable results over the past years. In NLP, especially Large …
Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in …
In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one-or two-armed robots equipped with multi-fingered hand …
Abstract Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. PBT is a single-objective algorithm, but many real-world hyperparameter …
A Mohan, C Benjamins, K Wienecke… - arXiv preprint arXiv …, 2023 - arxiv.org
Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often …
Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in …
X Wan, P Osselin, H Kenlay, B Ru… - Advances in …, 2023 - proceedings.neurips.cc
The increasing availability of graph-structured data motivates the task of optimising over functions defined on the node set of graphs. Traditional graph search algorithms can be …
H Bai, R Cheng - IEEE Transactions on Emerging Topics in …, 2024 - ieeexplore.ieee.org
Hyperparameter optimization plays a key role in the machine learning domain. Its significance is especially pronounced in reinforcement learning (RL), where agents …