感知与行动的统一:自由能原理概览介绍|自由能原理与强化学习读书会第一期

导语


分享内容简介
分享内容简介
—— 自由能原理提出者 Karl Friston
参考链接:https://medium.com/aimonks/deep-learning-is-rubbish-karl-friston-yann-lecun-face-off-at-davos-2024-world-economic-forum-494e82089d22
内容大纲
内容大纲
牟牧云:自由能原理与强化学习概览介绍
-
自然智能与人工智能:感知和行动的统一性原理?
-
导向主动推理的两条路径
-
大脑、生物系统、物理的自由能原理
-
预测加工理论
-
强化学习与自由能原理的联系:世界模型与探索
张德祥:自由能原理——从第一原理推导的庞大智能理论框架
-
自由能原理定义
-
类生物AGI实现进展简介
-
基础
-
自由能原理与相关的各个理论比较
-
自组织方向 目的 high road
-
⻉叶斯方向 机制 low road
-
自由能原理的世界模型层次观
核心概念
核心概念
-
自由能原理 Free Energy Principle
-
主动推理 Active inference
-
强化学习 Reinforcement learning
-
世界模型 World model
-
预测加工理论 Predictive processing theory
主讲人简介
主讲人简介


直播信息
直播信息

参考文献
参考文献
-
Parr, Thomas, Giovanni Pezzulo, and Karl J. Friston. Active inference: the free energy principle in mind, brain, and behavior. MIT Press, 2022.
-
Friston, K. The free-energy principle: a unified brain theory?. Nat Rev Neurosci 11, 127–138 (2010). https://doi.org/10.1038/nrn2787
-
Friston, Karl, James Kilner, and Lee Harrison. A free energy principle for the brain. Journal of physiology-Paris 100.1-3 (2006): 70-87.
-
Karl, Friston. A free energy principle for biological systems. Entropy 14.11 (2012): 2100-2121.
-
Friston, Karl. A free energy principle for a particular physics. arXiv preprint arXiv:1906.10184 (2019).
-
Parr, Thomas, and Karl J. Friston. Attention or salience?. Current opinion in psychology 29 (2019): 1-5.
-
Feldman, Harriet, and Karl J. Friston. Attention, uncertainty, and free-energy. Frontiers in human neuroscience 4 (2010): 215.
-
Clark, Andy, Surfing Uncertainty: Prediction, Action, and the Embodied Mind (New York, 2016; online edn, Oxford Academic, 22 Oct. 2015), https://doi.org/10.1093/acprof:oso/9780190217013.001.0001, accessed 19 Dec. 2023. (中译本《预测算法:具身智能如何应对不确定性》,机械工业出版社(2020))
-
Blakemore, Sarah-J., Chris D. Frith, and Daniel M. Wolpert. Spatio-temporal prediction modulates the perception of self-produced stimuli. Journal of cognitive neuroscience 11.5 (1999): 551-559.
-
Mazzaglia, Pietro, et al. The free energy principle for perception and action: A deep learning perspective. Entropy 24.2 (2022): 301.
-
Hafner D, Lillicrap T, Fischer I, et al. Learning latent dynamics for planning from pixels. ICML 2019
-
【Dreamer V1】Hafner D, Lillicrap T, Ba J, et al. Dream to control: Learning behaviors by latent imagination[J]. arXiv preprint arXiv:1912.01603, 2019.
-
【Dreamer V2】Hafner D, Lillicrap T, Norouzi M, et al. Mastering atari with discrete world models[J]. arXiv preprint arXiv:2010.02193, 2020.
-
【Dreamer V3】Hafner D, Pasukonis J, Ba J, et al. Mastering diverse domains through world models[J]. arXiv preprint arXiv:2301.04104, 2023.
-
Hao J, Yang T, Tang H, et al. Exploration in deep reinforcement learning: From single-agent to multiagent domain. IEEE Transactions on Neural Networks and Learning Systems, 2023.
-
Sekar R, Rybkin O, Daniilidis K, et al. Planning to explore via self-supervised world models. ICML 2020
-
Saxena V, Ba J, Hafner D. Clockwork variational autoencoders. NIPS 2021, 34: 29246-29257.

推荐阅读
自由能原理与强化学习读书会招募中

点击“阅读原文”,报名读书会





