The Barbados 2018 List of Open Issues in Continual Learning
Not on the map. Why?
Abstract (arXiv)
We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments. The purpose of this report is to sketch a research outline, share some of the most important open issues we are facing, and stimulate further discussion in the community. The content is based on some of our discussions during a week-long workshop held in Barbados in February 2018.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 0; 2026: 1.
7 papers.
- 2023A Definition of Continual Reinforcement Learningcited by 101
- 2024Three Dogmas of Reinforcement Learningcited by 14
- 2022Exploring through Random Curiosity with General Value Functionscited by 10
- 2022A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settingscited by 5
- 2022Probing Transfer in Deep Reinforcement Learning without Task Engineeringcited by 4
- 2023Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learningcited by 2
- 2026When Remembering and Planning are Worth it: Navigating under Changecited by 0
- 2026When Remembering and Planning are Worth it: Navigating under Change17 Feb 2026
- 2024Three Dogmas of Reinforcement Learning15 Jul 2024
- 2023A Definition of Continual Reinforcement Learning20 Jul 2023
- 2023Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning24 Jan 2023
- 2022Exploring through Random Curiosity with General Value Functions18 Nov 2022
- 2022Probing Transfer in Deep Reinforcement Learning without Task Engineering22 Oct 2022
- 2022A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings16 Jun 2022