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; how deeply to cover the extension chapters
3:00 Plan: factorial depth today, hierarchy next week
4:30 Dirichlet priors and parameter learning
6:00 Learning rates and homeostasis
7:30 Novelty and information gain
9:00 Precision on decision-making
10:30 Habits when evidence is weak
12:00 Factorial depth: inferring several things at once
15:00 Explore-exploit and the two-armed bandit
18:00 Risk-seeking vs. risk-averse choices
19:30 Initial beliefs: no bias toward either arm
21:00 State transitions (B) conditioned on actions
22:30 Encoding the absence of a hint
24:00 The agent observing its own choices
25:30 How factorial depth changes model setup
27:00 One A tensor per modality
30:00 Conditioning on combinations of hidden states
33:00 Risk and pragmatic value in expected free energy
34:30 Intuitive preference values
37:30 D: priors over initial states
42:00 Visualizing the A tensors
46:30 Reading the likelihoods: hint stage and better arm
52:30 Factors without actions
55:30 T-maze tasks and trials
58:30 Preferences: start, win and loss
1:00:00 Simulation results: beliefs about the better arm
1:04:30 What if the better arm switches
1:07:30 Markov processes and partial observability: history
1:12:00 Resources: multi-agent explore-exploit
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; how deeply to cover the extension chapters
3:00 Plan: factorial depth today, hierarchy next week
4:30 Dirichlet priors and parameter learning
6:00 Learning rates and homeostasis
7:30 Novelty and information gain
9:00 Precision on decision-making
10:30 Habits when evidence is weak
12:00 Factorial depth: inferring several things at once
15:00 Explore-exploit and the two-armed bandit
18:00 Risk-seeking vs. risk-averse choices
19:30 Initial beliefs: no bias toward either arm
21:00 State transitions (B) conditioned on actions
22:30 Encoding the absence of a hint
24:00 The agent observing its own choices
25:30 How factorial depth changes model setup
27:00 One A tensor per modality
30:00 Conditioning on combinations of hidden states
33:00 Risk and pragmatic value in expected free energy
34:30 Intuitive preference values
37:30 D: priors over initial states
42:00 Visualizing the A tensors
46:30 Reading the likelihoods: hint stage and better arm
52:30 Factors without actions
55:30 T-maze tasks and trials
58:30 Preferences: start, win and loss
1:00:00 Simulation results: beliefs about the better arm
1:04:30 What if the better arm switches
1:07:30 Markov processes and partial observability: history
1:12:00 Resources: multi-agent explore-exploit




