Deep reinforcement learning for cyber security

TT Nguyen, VJ Reddi - IEEE Transactions on Neural Networks …, 2021 - ieeexplore.ieee.org
The scale of Internet-connected systems has increased considerably, and these systems are
being exposed to cyberattacks more than ever. The complexity and dynamics of …

Learning task-state representations

Y Niv - Nature neuroscience, 2019 - nature.com
Arguably, the most difficult part of learning is deciding what to learn about. Should I
associate the positive outcome of safely completing a street-crossing with the situation 'the …

Learning heuristics for the tsp by policy gradient

M Deudon, P Cournut, A Lacoste, Y Adulyasak… - Integration of Constraint …, 2018 - Springer
The aim of the study is to provide interesting insights on how efficient machine learning
algorithms could be adapted to solve combinatorial optimization problems in conjunction …

Topology optimization via machine learning and deep learning: A review

S Shin, D Shin, N Kang - Journal of Computational Design and …, 2023 - academic.oup.com
Topology optimization (TO) is a method of deriving an optimal design that satisfies a given
load and boundary conditions within a design domain. This method enables effective design …

Latent learning, cognitive maps, and curiosity

MZ Wang, BY Hayden - Current Opinion in Behavioral Sciences, 2021 - Elsevier
Curiosity is a desire for information that is not motivated by strategic concerns. Latent
learning is not driven by standard reinforcement processes. We propose that curiosity serves …

Deep learning for cognitive neuroscience

KR Storrs, N Kriegeskorte - arXiv preprint arXiv:1903.01458, 2019 - arxiv.org
Neural network models can now recognise images, understand text, translate languages,
and play many human games at human or superhuman levels. These systems are highly …

Deep hierarchical reinforcement learning for autonomous driving with distinct behaviors

J Chen, Z Wang, M Tomizuka - 2018 IEEE intelligent vehicles …, 2018 - ieeexplore.ieee.org
Deep reinforcement learning has achieved great progress recently in domains such as
learning to play Atari games from raw pixel input. The model-free characteristics of …

Exploring the promise and limits of real-time recurrent learning

K Irie, A Gopalakrishnan, J Schmidhuber - arXiv preprint arXiv:2305.19044, 2023 - arxiv.org
Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks
(RNNs) offers certain conceptual advantages over backpropagation through time (BPTT) …

Behavioral priors and dynamics models: Improving performance and domain transfer in offline rl

C Cang, A Rajeswaran, P Abbeel, M Laskin - arXiv preprint arXiv …, 2021 - arxiv.org
Offline Reinforcement Learning (RL) aims to extract near-optimal policies from imperfect
offline data without additional environment interactions. Extracting policies from diverse …

Reliability-optimal offloading in low-latency edge computing networks: Analytical and reinforcement learning based designs

Y Zhu, Y Hu, T Yang, T Yang, J Vogt… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this paper, we consider a multi-access edge computing (MEC) network with multiple
servers. Due to the low latency constraints, the wireless data transmission/offloading is …