Uploaded September 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; Chapters 9 and 10 on discrete models
3:00 Recommended reading: the pymdp paper
7:30 How much of the book pymdp covers
10:30 Finding the code in the pymdp repository
12:00 How Chapter 10 builds on earlier chapters
13:30 Recap: learning A, B and D
15:00 What should and should not be learned
16:30 Recap: choosing among policies (Chapter 9)
18:00 Pragmatic value as reward
19:30 Ambiguity and the A matrix
21:00 Novelty
24:00 Parameters before and after experience
25:30 Seeking novel experiences
28:30 Example: where to look while driving home
31:30 Actions that elicit informative observations
33:00 Active inference and empirical behavior
34:30 Novelty for B and D: further resources
36:00 Novelty for one policy at one time step
37:30 Community code repository
39:00 Neurobiology figure
42:00 Dirichlet counts as a matrix like A
46:30 Broadcasting in pymdp
48:00 KL divergence and highest novelty
51:00 Fitting models to behavior
52:30 Learning preferences, habits and precision beyond pymdp
54:00 Habits (E) and Eq. 9.55
58:30 F: evidence for policies from past and present
1:00:00 F as reactive, G as planning
1:03:00 Confidence in plans
1:04:30 Zero confidence: falling back on habits
1:06:00 Wrap-up
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; Chapters 9 and 10 on discrete models
3:00 Recommended reading: the pymdp paper
7:30 How much of the book pymdp covers
10:30 Finding the code in the pymdp repository
12:00 How Chapter 10 builds on earlier chapters
13:30 Recap: learning A, B and D
15:00 What should and should not be learned
16:30 Recap: choosing among policies (Chapter 9)
18:00 Pragmatic value as reward
19:30 Ambiguity and the A matrix
21:00 Novelty
24:00 Parameters before and after experience
25:30 Seeking novel experiences
28:30 Example: where to look while driving home
31:30 Actions that elicit informative observations
33:00 Active inference and empirical behavior
34:30 Novelty for B and D: further resources
36:00 Novelty for one policy at one time step
37:30 Community code repository
39:00 Neurobiology figure
42:00 Dirichlet counts as a matrix like A
46:30 Broadcasting in pymdp
48:00 KL divergence and highest novelty
51:00 Fitting models to behavior
52:30 Learning preferences, habits and precision beyond pymdp
54:00 Habits (E) and Eq. 9.55
58:30 F: evidence for policies from past and present
1:00:00 F as reactive, G as planning
1:03:00 Confidence in plans
1:04:30 Zero confidence: falling back on habits
1:06:00 Wrap-up










