This volume constitutes the papers of the 3rd International Workshop on Active Inference, IWAI 2022, held in Grenoble, France, in conjunction with ECML/PKDD, on September 19, 2022.
The 25 revised full papers presented in this book were carefully reviewed and selected from 31 submissions.
Preventing Deterioration of Classification Accuracy in Predictive Coding
Networks.- Interpreting systems as solving POMDPs: a step towards a
formal understanding of agency.- Disentangling Shape and Pose for
Object-Centric Deep Active Inference Models.- Object-based Active
Inference.- Knitting a Markov blanket is hard when you are
out-of-equilibrium: two examples in canonical nonequilibrium models.- Spin
glass systems as collective active inference.- Mapping Husserlian
phenomenology onto active inference.- The Role of Valence and Meta-awareness
in Mirror Self-recognition Using Hierarchical Active Inference.- World model
learning from demonstrations with active inference: application to driving
behavior.- Active Blockference: cadCAD with Active Inference for
cognitive systems modeling.- Active Inference Successor Representations.-
Learning Policies for Continuous Control via Transition Models.- Attachment
Theory in anActive Inference Framework: How Does Our Inner Model Take
Shape?.- Capsule Networks as Generative Models.- Home run: finding your way
home by imagining trajectories.- A Novel Model for Novelty: Modeling the
Emergence of Innovation from Cumulative Culture.- Active Inference and
Psychology of Expectations: A study of formalizing ViolEx.- AIXI, FEP-AI, and
integrated world models: Towards a unified understanding of intelligence and
consciousness.- Intention Modulation for Multi-Step Tasks in Continuous Time
Active Inference.- Learning Generative Models for Active Inference using
Tensor Networks.- A Worked Example of the Bayesian Mechanics of Classical
Objects.- A message passing perspective on planning under Active Inference.-
Efficient search of active inference policy spaces using k-means.- Value
Cores for Inner and Outer Alignment: Simulating Personality Formation via
Iterated Policy Selection and Preference Learning with Self-World Modeling
Active Inference Agent.- Deriving time-averaged active inference from control
principles.
