Uploaded October 2026 | Updated November 2026, 1 day 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 and plan
3:00 Sophisticated inference as an alternative objective
4:30 Chapter 11 notes: modifying discrete-state active inference
7:30 Recap: choosing policies by expected free energy and habits
9:00 Beliefs about future hidden states
10:30 The recursive expected free energy
15:00 Planning one step at a time with expected observations
16:30 Tree search and pruning
18:00 Sophisticated inference example in the pymdp docs
22:30 Tractability and biological plausibility
24:00 Inductive planning: reasoning back from goal states
27:00 Testing goal reachability with the B tensor
31:30 Priors over policies
33:00 State-based prior preferences
34:30 Learning preferences and planning precision
36:00 The full POMDP active inference picture
37:30 Habits and habit learning
42:00 Preferences across the planning horizon
46:30 Learning and forgetting rates; precision on A and B
49:30 Coarse-graining policies
51:00 Mixed models: from decisions to movement and back
54:00 Tree-based policy selection and Monte Carlo tree search
57:00 Design choices: multifactorial and hierarchical models
58:30 Discussion: adding hidden states and model comparison
1:06:00 Discussion: compositional active inference
1:09:00 Structure learning: growing a model from observations
1:13:30 Wrap-up; next week Chapter 12
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 and plan
3:00 Sophisticated inference as an alternative objective
4:30 Chapter 11 notes: modifying discrete-state active inference
7:30 Recap: choosing policies by expected free energy and habits
9:00 Beliefs about future hidden states
10:30 The recursive expected free energy
15:00 Planning one step at a time with expected observations
16:30 Tree search and pruning
18:00 Sophisticated inference example in the pymdp docs
22:30 Tractability and biological plausibility
24:00 Inductive planning: reasoning back from goal states
27:00 Testing goal reachability with the B tensor
31:30 Priors over policies
33:00 State-based prior preferences
34:30 Learning preferences and planning precision
36:00 The full POMDP active inference picture
37:30 Habits and habit learning
42:00 Preferences across the planning horizon
46:30 Learning and forgetting rates; precision on A and B
49:30 Coarse-graining policies
51:00 Mixed models: from decisions to movement and back
54:00 Tree-based policy selection and Monte Carlo tree search
57:00 Design choices: multifactorial and hierarchical models
58:30 Discussion: adding hidden states and model comparison
1:06:00 Discussion: compositional active inference
1:09:00 Structure learning: growing a model from observations
1:13:30 Wrap-up; next week Chapter 12










