Deep learning, reinforcement learning, and world models

By Yu Matsuo, Yann LeCun, Maneesh Sahani, Doina Precup, David Silver, Masashi Sugiyama, Eiji Uchibe, Jun Morimoto. Neural Networks, 2022

503 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/effa7077e6580a8ab22c30d3c876744b4e51cd6e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yu Qiao
2. Xiaogang Wang
3. Jianfeng Gao
4. Jifeng Dai
5. Gao Huang
6. Luc Van Gool
7. Chunhua Shen
8. Alan L. Yuille

In Cognitive Neuroscience

1. Yu Qiao
2. Bin Li
3. Xiaogang Wang

Citations in the corpus

• Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey (2025, unknown): “Reinforcement Learning (RL) [13] is central to many agentic systems, as it equips AI models with the ability to learn through trial and error.”
• Reasoning with Language Model is Planning with World Model (2023, background): “In general, a world model predicts the next state of the reasoning after applying an action to the current state (Ha and Schmidhuber, 2018b; Matsuo et al., 2022).”
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory (2023, background): “Although reinforcement learning (RL) [16] is the most popular paradigm for approaching GCAs, it has shown some staggering limitations in conquering Minecraft.”