Decaf: deep case-based policy inference for knowledge transfer in reinforcement learning

R Glatt, FL Da Silva, RA da Costa Bianchi… - Expert Systems with …, 2020 - Elsevier
Having the ability to solve increasingly complex problems using Reinforcement Learning
(RL) has prompted researchers to start develo** a greater interest in systematic …

A study on efficient reinforcement learning through knowledge transfer

R Glatt, FL da Silva, RA da Costa Bianchi… - Federated and Transfer …, 2022 - Springer
Abstract Although Reinforcement Learning (RL) algorithms have made impressive progress
in learning complex tasks over the past years, there are still prevailing short-comings and …

Performance evaluation of machine learning algorithms in Apache spark for intrusion detection

A Dobson, K Roy, X Yuan, J Xu - 2018 28th International …, 2018 - ieeexplore.ieee.org
As the Internet continues to get stronger, so does the potential risk of malicious users trying
to harm others. An intrusion detection system (IDS) can be used to alert the appropriate …

Interpolation-Assisted Evolutionary Rule-Based Machine Learning-Strategies to Counter Knowledge Gaps in XCS-Based Self-Learning Adaptive Systems

A Stein - 2019 - opus.bibliothek.uni-augsburg.de
Self-adaptive systems are increasingly endowed with Artificial Intelligence technology in
order to enhance system autonomy. Most prominently, algorithms from the research field of …

A framework to discover and reuse object-oriented options in reinforcement learning

R Bonini, FL Da Silva, R Glatt, E Spina… - 2018 7th Brazilian …, 2018 - ieeexplore.ieee.org
Reinforcement Learning is a successful yet slow technique to train autonomous agents.
Option-based solutions can be used to accelerate learning and to transfer learned behaviors …

[PDF][PDF] Knowledge reuse for Deep Reinforcement Learning

R Glatt - 2019 - researchgate.net
With the rise of Deep Learning the field of Artificial Intelligence (AI) Research has entered a
new era. Together with an increasing amount of data and vastly improved computing …

[PDF][PDF] Descoberta e reuso de políticas parciais probabilísticas no aprendizado por reforço.

RC Bonini - 2018 - researchgate.net
RESUMO O aprendizado por reforço é uma técnica bem sucedida, porém lenta, para treinar
agentes autônomos. Algumas soluções baseadas em políticas parciais podem ser usadas …