Uploaded September 2026 | Updated November 2026, 20 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; the Ryan Smith et al. tutorial
3:00 From continuous to discrete state-space models
4:30 One observation modality, one hidden-state factor
6:00 Three weeks on Chapter 9; building A and B
7:30 Recap: observation and state-transition models
9:00 Actions give the agent control
10:30 Example: preferences and actions
12:00 The initial-state prior (D)
13:30 Preferences over observations (C)
15:00 Softmax-normalizing preferences
16:30 Expected future observations
18:00 Expected free energy: two terms
19:30 Why VFE covers only the past and present
21:00 Risk and ambiguity
22:30 Risk as divergence from preferences
24:00 Ambiguity from the A matrix
25:30 Uninformative observations
28:30 Matrix operations for expected free energy
30:00 Expected free energy for each policy
31:30 Habits (E), previewed for Chapter 10
33:00 The full model: D, A, B and policies
34:30 Links to concepts in other fields
36:00 Reward-only agents and local optima
37:30 Exploitation: will this policy get what I want
39:00 Seeking information
40:30 Comparison with epsilon-greedy exploration
42:00 Balancing risk and ambiguity
45:00 Discussion: what counts as reward
46:30 Equivalent forms of expected free energy
48:00 Worked example: near-equivalent likelihoods
49:30 Preview of Chapter 10
51:00 Resources: POMDP tutorials
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; the Ryan Smith et al. tutorial
3:00 From continuous to discrete state-space models
4:30 One observation modality, one hidden-state factor
6:00 Three weeks on Chapter 9; building A and B
7:30 Recap: observation and state-transition models
9:00 Actions give the agent control
10:30 Example: preferences and actions
12:00 The initial-state prior (D)
13:30 Preferences over observations (C)
15:00 Softmax-normalizing preferences
16:30 Expected future observations
18:00 Expected free energy: two terms
19:30 Why VFE covers only the past and present
21:00 Risk and ambiguity
22:30 Risk as divergence from preferences
24:00 Ambiguity from the A matrix
25:30 Uninformative observations
28:30 Matrix operations for expected free energy
30:00 Expected free energy for each policy
31:30 Habits (E), previewed for Chapter 10
33:00 The full model: D, A, B and policies
34:30 Links to concepts in other fields
36:00 Reward-only agents and local optima
37:30 Exploitation: will this policy get what I want
39:00 Seeking information
40:30 Comparison with epsilon-greedy exploration
42:00 Balancing risk and ambiguity
45:00 Discussion: what counts as reward
46:30 Equivalent forms of expected free energy
48:00 Worked example: near-equivalent likelihoods
49:30 Preview of Chapter 10
51:00 Resources: POMDP tutorials










