Deep learning, reinforcement learning, and world models

Yu Matsuo, Yann LeCun, M. Sahani, Doina Precup, David Silver, Masashi Sugiyama et al.

2022 Neural Networks Cited 451 times

Abstract

Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable factors to achieve human-level or super-human AI systems. On the other hand, both DL and RL have strong connections with our brain functions and with neuroscientific findings. In this review, we summarize talks and discussions in the "Deep Learning and Reinforcement Learning" session of the symposium, International Symposium on Artificial Intelligence and Brain Science. In this session, we discussed whether we can achieve comprehensive understanding of human intelligence based on the recent advances of deep learning and reinforcement learning algorithms. Speakers contributed to provide talks about their recent studies that can be key technologies to achieve human-level intelligence.

BibTeX

@article{Matsuo2022,
  author = {Matsuo, Yutaka and LeCun, Yann and Sahani, Maneesh and Precup, Doina and Silver, David and Sugiyama, Masashi and Uchibe, Eiji and Morimoto, Jun},
  journal = {Neural Networks},
  title = {Deep learning, reinforcement learning, and world models},
  year = {2022},
  publisher = {Elsevier},
}