Dual regularized policy updating and shiftpoint detection for automated deployment of reinforcement learning controllers on industrial mechatronic systems

V Vantilborgh, T Staessens, W De Groote… - Control Engineering …, 2024 - Elsevier
We propose an algorithmic pipeline enabling deep reinforcement learning controllers to
detect when a significant change in system characteristics has occurred and update the …

[HTML][HTML] Evaluating semi-cooperative Nash/Stackelberg Q-learning for traffic routes plan in a single intersection

J Guo, I Harmati - Control Engineering Practice, 2020 - Elsevier
As traffic congestion grows tremendous and frequent in the urban transportation system,
many efficient models with reinforcement learning (RL) methods have already been …

Q-learning with experience replay in a dynamic environment

M Pieters, MA Wiering - 2016 IEEE Symposium Series on …, 2016 - ieeexplore.ieee.org
Most research in reinforcement learning has focused on stationary environments. In this
paper, we propose several adaptations of Q-learning for a dynamic environment, for both …

Active perception in adversarial scenarios using maximum entropy deep reinforcement learning

M Shen, JP How - 2019 International Conference on Robotics …, 2019 - ieeexplore.ieee.org
We pose an active perception problem where an autonomous agent actively interacts with a
second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the …

A deep recurrent Q network towards self‐adapting distributed microservice architecture

B Magableh, M Almiani - Software: Practice and Experience, 2020 - Wiley Online Library
One desired aspect of microservice architecture is the ability to self‐adapt its own
architecture and behavior in response to changes in the operational environment. To …

Decentralized multi-agent actor-critic with generative inference

K Corder, MM Vindiola, K Decker - arXiv preprint arXiv:1910.03058, 2019 - arxiv.org
Recent multi-agent actor-critic methods have utilized centralized training with decentralized
execution to address the non-stationarity of co-adapting agents. This training paradigm …

Optimization of traffic signal control based on game theoretical framework

J Guo, I Harmati - … Conference on Methods and Models in …, 2019 - ieeexplore.ieee.org
This paper presents a model of intelligent traffic signal control using a game theoretical
framework based on decision-making operations. This model aims at finding an optimal …

Optimization of traffic signal control with different game theoretical strategies

J Guo, I Harmati - … Conference on System Theory, Control and …, 2019 - ieeexplore.ieee.org
This paper presents a model of intelligent traffic signal control using a game theoretical
framework based on decision-making combinations. This model aims at finding an optimal …

[PDF][PDF] Multi-agent traffic control using game theory and reinforcement learning

GUO Jian - 2022 - repozitorium.omikk.bme.hu
The intelligent transportation system has recently received more attention, which plays an
important role in easing traffic congestion. Regulating traffic flow effectively and efficiently is …

Private and Provably Efficient Federated Decision-Making

A Dubey - 2022 - dspace.mit.edu
In this thesis, we study sequential multi-armed bandit and reinforcement learning in the
federated setting, where a group of agents collaborates to improve their collective reward by …