Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents

AAAI 2018 pp. 7983-7987

doi:10.1609/AAAI.V32I1.12219 /aaai/2018/laird2018aaai-learning/

Abstract

We propose two distinct levels of learning for general autonomous intelligent agents. Level 1 consists of fixed architectural learning mechanisms that are innate and automatic. Level 2 consists of deliberate learning strategies that are controlled by the agent's knowledge. We describe these levels and provide an example of their use in a task-learning agent. We also explore other potential levels and discuss the implications of this view of learning for the design of autonomous agents.

PDF AAAI Semantic Scholar

Cite

Text

Laird and Mohan. "Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12219

Markdown

[Laird and Mohan. "Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/laird2018aaai-learning/) doi:10.1609/AAAI.V32I1.12219

BibTeX

@inproceedings{laird2018aaai-learning,
  title     = {{Learning Fast and Slow: Levels of Learning in General Autonomous Intelligent Agents}},
  author    = {Laird, John E. and Mohan, Shiwali},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {7983-7987},
  doi       = {10.1609/AAAI.V32I1.12219},
  url       = {https://mlanthology.org/aaai/2018/laird2018aaai-learning/}
}