Designing Explainable Artificial Intelligence with Active Inference: A Framework for Transparent Introspection and Decision-Making

Albarracin, Mahault; Hipólito, Inês; Tremblay, Safae Essafi; Fox, Jason G.; René, Gabriel; Friston, Karl; Ramstead, Maxwell J. D.

doi:10.1007/978-3-031-47958-8_9

Cited by 8 publications

(2 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An additional advantage of the mixed model proposed (and the POMDP-based generative models) is that we can probe the model parameters to understand the basis of intelligent behaviour demonstrated by agents through the lens of active inference [ 28 , 29 , 30 ]. Models that rely on artificial neural networks (ANNs) to scale up the models [ 31 ] have limited explainability regarding how agents make decisions, especially when faced with uncertainty.…”

Section: Resultsmentioning

confidence: 99%

On Predictive Planning and Counterfactual Learning in Active Inference

Paul,

Isomura,

Razi

2024

Entropy

View full text Add to dashboard Cite

Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. This paper examines two decision-making schemes in active inference based on “planning” and “learning from experience”. Furthermore, we also introduce a mixed model that navigates the data complexity trade-off between these strategies, leveraging the strengths of both to facilitate balanced decision-making. We evaluate our proposed model in a challenging grid-world scenario that requires adaptability from the agent. Additionally, our model provides the opportunity to analyse the evolution of various parameters, offering valuable insights and contributing to an explainable framework for intelligent decision-making.

show abstract

Section: Resultsmentioning

confidence: 99%

On Predictive Planning and Counterfactual Learning in Active Inference

Paul,

Isomura,

Razi

2024

Entropy

View full text Add to dashboard Cite

show abstract

“…The design space for incorporating techniques from contemporary generative AI in active inference models is large and the exploration of these possibilities has only begun (see e.g., Fountas et al, 2020 ; Tschantz et al, 2020 ; Lanillos et al, 2021 ; Friston et al, 2022 ; Mazzaglia et al, 2022 ). However, regardless of the implementation, behavioral models developed based on the active inference principles outlined above are fundamentally explainable and interpretable which is one of their key potential advantages compared to existing black-box approaches for agent modeling (Albarracin et al, 2023 ).…”

Section: Discussionmentioning

confidence: 99%

Resolving uncertainty on the fly: modeling adaptive driving behavior as active inference

Engström,

Wei,

McDonald

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles. However, existing traffic psychology models of adaptive driving behavior either lack computational rigor or only address specific scenarios and/or behavioral phenomena. While models developed in the fields of machine learning and robotics can effectively learn adaptive driving behavior from data, due to their black box nature, they offer little or no explanation of the mechanisms underlying the adaptive behavior. Thus, generalizable, interpretable, computational models of adaptive human driving behavior are still rare. This paper proposes such a model based on active inference, a behavioral modeling framework originating in computational neuroscience. The model offers a principled solution to how humans trade progress against caution through policy selection based on the single mandate to minimize expected free energy. This casts goal-seeking and information-seeking (uncertainty-resolving) behavior under a single objective function, allowing the model to seamlessly resolve uncertainty as a means to obtain its goals. We apply the model in two apparently disparate driving scenarios that require managing uncertainty, (1) driving past an occluding object and (2) visual time-sharing between driving and a secondary task, and show how human-like adaptive driving behavior emerges from the single principle of expected free energy minimization.

show abstract