Uploaded September 2026 | Updated November 2026, 10 hours 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
1:30 Finishing 10.1: novelty
3:00 Notes for section 10.2
4:30 Code notebook for Examples 10.1 to 10.4
6:00 Recap: the POMDP with policies
9:00 Information gain: how informative is an observation
10:30 Expected free energy over the time horizon
13:30 Action selection: first action of the best policy
15:00 Learning A, B and D
16:30 Policy posterior vs. prior
18:00 The novelty term in expected free energy
19:30 Simplifying assumption: novelty for A only
21:00 Computing novelty in code (Algorithm 19)
24:00 Prior over policies vs. planned policies
25:30 Combining variational and expected free energy over policies
30:00 Trading off F, G and habits
31:30 Policy precision (gamma)
33:00 Habits (E)
37:30 Policy posteriors as gamma varies
40:30 When habits conflict with expected free energy
43:30 Q&A: a very high-precision habit prior
46:30 Log-transformed habits alongside F and G
49:30 Learning confidence in habits
52:30 Learning policy precision
54:00 The gamma distribution prior
55:30 Updating precision from free energy
57:00 Example: weak habits
58:30 Next: factorial and 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
1:30 Finishing 10.1: novelty
3:00 Notes for section 10.2
4:30 Code notebook for Examples 10.1 to 10.4
6:00 Recap: the POMDP with policies
9:00 Information gain: how informative is an observation
10:30 Expected free energy over the time horizon
13:30 Action selection: first action of the best policy
15:00 Learning A, B and D
16:30 Policy posterior vs. prior
18:00 The novelty term in expected free energy
19:30 Simplifying assumption: novelty for A only
21:00 Computing novelty in code (Algorithm 19)
24:00 Prior over policies vs. planned policies
25:30 Combining variational and expected free energy over policies
30:00 Trading off F, G and habits
31:30 Policy precision (gamma)
33:00 Habits (E)
37:30 Policy posteriors as gamma varies
40:30 When habits conflict with expected free energy
43:30 Q&A: a very high-precision habit prior
46:30 Log-transformed habits alongside F and G
49:30 Learning confidence in habits
52:30 Learning policy precision
54:00 The gamma distribution prior
55:30 Updating precision from free energy
57:00 Example: weak habits
58:30 Next: factorial and hierarchical depth










