Full Description
This book constitutes the revised selected papers of the 5th International Workshop on Active Inference, IWAI 2024, held in Oxford, UK, during September 9-11, 2024.
The 17 full papers included in this book were carefully reviewed and selected from 54 submissions. They were organized in topical sections as follows: Modeling Behaviour and Emotions; Hybrid Continuous-discrete Systems; Structure Learning; Multi-agent Systems; Epistemic Sampling; Robot Control; and Sustainability and Contextuality.
Contents
.- Modeling behaviour and emotions.
.- Towards Interaction Design with Active Inference: A Case Study on Noisy Ordinal Selection.
.- Modelling Agency Perception in Depression Using Active Inference: A Multi-Agent Behavioural Study.
.- Free Energy in a Circumplex Model of Emotions.
.- Hybrid continuous-discrete systems.
.- Learning in Hybrid Active Inference Models.
.- Learning and embodied decisions in active inference.
.- Structure learning.
.- Online Structure Learning with Dirichlet Processes through Message Passing.
.- Exploring and Learning Structure: Active Inference Approach in Navigational Agents.
.- Multi-agent systems.
.- Belief sharing: a blessing or a curse.
.- Coupled autoregressive active inference agents for control of multi-joint dynamical systems.
.- Reactive Environments for Active Inference Agents with RxEnvironments.
.- Epistemic sampling.
.- Selection of Exploratory or Goal-Directed Behavior by a Physical Robot Implementing Deep Active Inference.
.- Epistemic Value Anticipation into the Deep Active Inference Model.
.- Robot control.
.- Planning to avoid ambiguous states through Gaussian approximations to non-linear sensors in active inference agents.
.- Message Passing-based Bayesian Control of a Cart-Pole System.
.- Reducing Intuitive-Physics Prediction Error through Playing.
.- Sustainability and contextuality.
.- Modeling Sustainability under Active Inference through resource management.
.- Contextuality, Cognitive engagement, and Active Inference.
