Magnetic control of tokamak plasmas through deep reinforcement learning

J Degrave, F Felici, J Buchli, M Neunert, B Tracey… - Nature, 2022‏ - nature.com
Nuclear fusion using magnetic confinement, in particular in the tokamak configuration, is a
promising path towards sustainable energy. A core challenge is to shape and maintain a …

Outracing champion Gran Turismo drivers with deep reinforcement learning

PR Wurman, S Barrett, K Kawamoto, J MacGlashan… - Nature, 2022‏ - nature.com
Many potential applications of artificial intelligence involve making real-time decisions in
physical systems while interacting with humans. Automobile racing represents an extreme …

Acme: A research framework for distributed reinforcement learning

MW Hoffman, B Shahriari, J Aslanides… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Deep reinforcement learning (RL) has led to many recent and groundbreaking advances.
However, these advances have often come at the cost of both increased scale in the …

Beyond supervised continual learning: a review

B Bagus, A Gepperth, T Lesort - arxiv preprint arxiv:2208.14307, 2022‏ - arxiv.org
Continual Learning (CL, sometimes also termed incremental learning) is a flavor of machine
learning where the usual assumption of stationary data distribution is relaxed or omitted …

Open source vizier: Distributed infrastructure and api for reliable and flexible blackbox optimization

X Song, S Perel, C Lee, G Kochanski… - International …, 2022‏ - proceedings.mlr.press
Vizier is the de-facto blackbox optimization service across Google, having optimized some of
Google's largest products and research efforts. To operate at the scale of tuning thousands …

Whole-body simulation of realistic fruit fly locomotion with deep reinforcement learning

R Vaxenburg, I Siwanowicz, J Merel, AA Robie… - bioRxiv, 2024‏ - biorxiv.org
The body of an animal influences how the nervous system produces behavior. Therefore,
detailed modeling of the neural control of sensorimotor behavior requires a detailed model …

Active offline policy selection

K Konyushova, Y Chen, T Paine… - Advances in …, 2021‏ - proceedings.neurips.cc
This paper addresses the problem of policy selection in domains with abundant logged data,
but with a restricted interaction budget. Solving this problem would enable safe evaluation …

Phantom--A RL-driven multi-agent framework to model complex systems

L Ardon, J Vann, D Garg, T Spooner… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Agent based modelling (ABM) is a computational approach to modelling complex systems
by specifying the behaviour of autonomous decision-making components or agents in the …

Increasing the safety of adaptive cruise control using physics-guided reinforcement learning

SL Jurj, D Grundt, T Werner, P Borchers, K Rothemann… - Energies, 2021‏ - mdpi.com
This paper presents a novel approach for improving the safety of vehicles equipped with
Adaptive Cruise Control (ACC) by making use of Machine Learning (ML) and physical …

GEAR: a GPU-centric experience replay system for large reinforcement learning models

H Wang, MK Sit, C He, Y Wen… - International …, 2023‏ - proceedings.mlr.press
This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed
to perform scalable reinforcement learning (RL) with large sequence models (such as …