A Study on Efficient Reinforcement Learning Through Knowledge Transfer
Nenhuma Miniatura disponível
Citações na Scopus
0
Tipo de produção
Capítulo de livro
Data
2022-10-05
Autores
GLATT, R.
DA SILVA, F. L.
Reinaldo Bianchi
COSTA, A. H. R.
DA SILVA, F. L.
Reinaldo Bianchi
COSTA, A. H. R.
Orientador
Periódico
Adaptation, Learning, and Optimization
Título da Revista
ISSN da Revista
Título de Volume
Citação
GLATT, R.; DA SILVA, F. L.; BIANCHI, R. COSTA, A. H. R. A Study on Efficient Reinforcement Learning Through Knowledge Transfer. Adaptation, Learning, and Optimization, v. 27, p. 329-356, oct. 2022.
Texto completo (DOI)
Palavras-chave
Resumo
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Although Reinforcement Learning (RL) algorithms have made impressive progress in learning complex tasks over the past years, there are still prevailing short-comings and challenges. Specifically, the sample-inefficiency and limited adaptation across tasks often make classic RL techniques impractical for real-world applications despite the gained representational power when combining deep neural networks with RL, known as Deep Reinforcement Learning (DRL). Recently, a number of approaches to address those issues have emerged. Many of those solutions are based on smart DRL architectures that enhance single task algorithms with the capability to share knowledge between agents and across tasks by introducing Transfer Learning (TL) capabilities. This survey addresses strategies of knowledge transfer from simple parameter sharing to privacy preserving federated learning and aims at providing a general overview of the field of TL in the DRL domain, establishes a classification framework, and briefly describes representative works in the area.