Towards Continual Reinforcement Learning: A Review and Perspectives

DOI10.1613/JAIR.1.13673MaRDI QIDQ5870519zbMATH OpenOpenAlexFDO

Authors Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

Publication date 9 January 2023

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.13490

zbMATH Keywords

Markov decision processesreinforcement learning

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• CHILD: A first step towards continual learning
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Curriculum learning for reinforcement learning domains: a framework and survey
• An introduction to deep reinforcement learning
• Scalable transfer learning in heterogeneous, dynamic environments

Cited in

(4)

• CVPR 2020 continual learning in computer vision competition: approaches, results, current challenges and future directions
• Sampled-data funnel control and its use for safe continual learning
• Continual learning as computationally constrained reinforcement learning
• The complexity of non-stationary reinforcement learning

This page was built for publication: Towards Continual Reinforcement Learning: A Review and Perspectives

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5870519)