Uploaded October 2026 | Updated November 2026, 2 days ago
Book: Fundamentals of Active Inference
Principles, Algorithms, and Applications of the Free Energy Principle for Engineers, by Sanjeev V. Namjoshi https://mitpress.mit.edu/9780262050951/fundamentals-of-active-inference/
Register: http://textbook-group.activeinference.institute/
Code: github.com/ActiveInferenceInstitute/fundamentals
Playlist of Textbook Group: youtube.com/playlist?list=PLNm0u2n1IwdrpoTg-9l37YIBiDrrOzTw-
Direct link to group document: coda.io/d/_dZHp_UGhVZE/Meetings_su3ToqMp
------
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Welcome; Chapter 10: extending our models
3:00 Notation conventions
4:30 Recap: scoring plans by expected free energy
6:00 Sign conventions: minimizing expected free energy
7:30 Policy precision (gamma) and habits
9:00 The code in Google Colab
10:30 The gamma distribution (see the appendix)
13:30 Variational vs. expected free energy of plans
16:30 Mixtures between the extreme cases
18:00 The POMDP graphical model
19:30 Multiple hidden-state factors
21:00 Multifactor model equations
24:00 Multiple observation modalities
27:00 Factorized posterior over hidden states
30:00 Discussion: building intuition for POMDPs
33:00 Example 10.12: the two-armed bandit
34:30 Model structure: context and choice factors
37:30 Figure 10.13 and the model on page 275
40:30 State transitions (B) for each factor
42:00 Preferences: reward, no reward, start
45:00 The observation likelihood tensor
51:00 Likelihood vs. inverse inference
54:00 Simulation results: context beliefs and expected free energy
58:30 Factorial vs. hierarchical depth
1:00:00 Discussion: agents modeling their own actions
1:03:00 Discussion: exploring vs. exploiting across modalities
1:07:30 Next: adding hierarchical depth
Book: Fundamentals of Active Inference
Principles, Algorithms, and Applications of the Free Energy Principle for Engineers, by Sanjeev V. Namjoshi https://mitpress.mit.edu/9780262050951/fundamentals-of-active-inference/
Register: http://textbook-group.activeinference.institute/
Code: github.com/ActiveInferenceInstitute/fundamentals
Playlist of Textbook Group: youtube.com/playlist?list=PLNm0u2n1IwdrpoTg-9l37YIBiDrrOzTw-
Direct link to group document: coda.io/d/_dZHp_UGhVZE/Meetings_su3ToqMp
------
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Welcome; Chapter 10: extending our models
3:00 Notation conventions
4:30 Recap: scoring plans by expected free energy
6:00 Sign conventions: minimizing expected free energy
7:30 Policy precision (gamma) and habits
9:00 The code in Google Colab
10:30 The gamma distribution (see the appendix)
13:30 Variational vs. expected free energy of plans
16:30 Mixtures between the extreme cases
18:00 The POMDP graphical model
19:30 Multiple hidden-state factors
21:00 Multifactor model equations
24:00 Multiple observation modalities
27:00 Factorized posterior over hidden states
30:00 Discussion: building intuition for POMDPs
33:00 Example 10.12: the two-armed bandit
34:30 Model structure: context and choice factors
37:30 Figure 10.13 and the model on page 275
40:30 State transitions (B) for each factor
42:00 Preferences: reward, no reward, start
45:00 The observation likelihood tensor
51:00 Likelihood vs. inverse inference
54:00 Simulation results: context beliefs and expected free energy
58:30 Factorial vs. hierarchical depth
1:00:00 Discussion: agents modeling their own actions
1:03:00 Discussion: exploring vs. exploiting across modalities
1:07:30 Next: adding hierarchical depth










