Uploaded October 2026 | Updated November 2026, 16 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 back; recap of Chapter 10 and the two-armed bandit
3:00 Topics added during the Chapter 10 sessions
4:30 Schedule: one week per remaining chapter, then a break
6:00 What draws people to active inference
7:30 Chapter 11: modifications and extensions
10:30 Variational free energy as an objective
12:00 The debate over planning objectives
15:00 Extending free energy into the future
16:30 Exploration terms in expected free energy
18:00 Eq. 11.3: why a naive future free energy discourages exploration
24:00 Papers that justify VFE and EFE
25:30 Mean-field factorizations across objectives
27:00 Fictive planning and far-fetched futures
30:00 Divergences, past and future observations
33:00 Likelihoods for not-yet-observed outcomes
36:00 Message passing throughout the book
39:00 Bethe free energy: keeping graph dependencies
40:30 Example: hunger signals by day and night
43:30 Constrained Bethe free energy
46:30 Rethinking how agents plan
49:30 Sophisticated inference: planning step by step
52:30 Pruning low-probability actions
54:00 pymdp sophisticated inference notebook (JAX)
1:00:00 The pruning threshold
1:01:30 Grid-world notebook
1:03:00 Learning rates and preference learning
1:04:30 Chapter 11 questions in the group document
1:06:00 Structure learning: expanding the model
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 back; recap of Chapter 10 and the two-armed bandit
3:00 Topics added during the Chapter 10 sessions
4:30 Schedule: one week per remaining chapter, then a break
6:00 What draws people to active inference
7:30 Chapter 11: modifications and extensions
10:30 Variational free energy as an objective
12:00 The debate over planning objectives
15:00 Extending free energy into the future
16:30 Exploration terms in expected free energy
18:00 Eq. 11.3: why a naive future free energy discourages exploration
24:00 Papers that justify VFE and EFE
25:30 Mean-field factorizations across objectives
27:00 Fictive planning and far-fetched futures
30:00 Divergences, past and future observations
33:00 Likelihoods for not-yet-observed outcomes
36:00 Message passing throughout the book
39:00 Bethe free energy: keeping graph dependencies
40:30 Example: hunger signals by day and night
43:30 Constrained Bethe free energy
46:30 Rethinking how agents plan
49:30 Sophisticated inference: planning step by step
52:30 Pruning low-probability actions
54:00 pymdp sophisticated inference notebook (JAX)
1:00:00 The pruning threshold
1:01:30 Grid-world notebook
1:03:00 Learning rates and preference learning
1:04:30 Chapter 11 questions in the group document
1:06:00 Structure learning: expanding the model










