paper:doi-10-1016-j-mehy-2014-12-007Optimal inference with suboptimal models: Addiction and active Bayesian inference
Original abstract (expand)
When casting behaviour as active (Bayesian) inference, optimal inference is defined with respect to an agent's beliefs - based on its generative model of the world. This contrasts with normative accounts of choice behaviour, in which optimal actions are considered in relation to the true structure of the environment - as opposed to the agent's beliefs about worldly states (or the task). This distinction shifts an understanding of suboptimal or pathological behaviour away from aberrant inference as such, to understanding the prior beliefs of a subject that cause them to behave less 'optimally' than our prior beliefs suggest they should behave. Put simply, suboptimal or pathological behaviour does not speak against understanding behaviour in terms of (Bayes optimal) inference, but rather calls for a more refined understanding of the subject's generative model upon which their (optimal) Bayesian inference is based. Here, we discuss this fundamental distinction and its implications for understanding optimality, bounded rationality and pathological (choice) behaviour. We illustrate our argument using addictive choice behaviour in a recently described 'limited offer' task. Our simulations of pathological choices and addictive behaviour also generate some clear hypotheses, which we hope to pursue in ongoing empirical work.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Active inference and artificial reasoningLancelot Da Costa, Alexander Tschantz, Conor Heins, Christopher Buckley, Tim Verbelen, Thomas Parr Karl Friston2025≈ 80%
- ≈ 80%
- ≈ 78%
- An empirical evaluation of active inference in multi-armed banditsHrvoje Stojic, Sarah Schwoebel, and Stefan J. Kiebel Dimitrije Markovic2021≈ 78%
- Active inference, Bayesian optimal design, and expected utilityLancelot Da Costa, Thomas Parr, Karl Friston Noor Sajid2021≈ 78%
- Reward Maximisation through Discrete Active InferenceNoor Sajid, Thomas Parr, Karl Friston, Ryan Smith Lancelot Da Costa2022≈ 78%
- Active Inference, Curiosity and Insightin corpus2017≈ 77%
- Active Inference for Binary Symmetric Hidden Markov ModelsArmen E. Allahverdyan and Aram Galstyan2015≈ 77%
- ≈ 77%
- Active inference: demystified and comparedin corpus2021≈ 77%
- Active Inference or Control as Inference? A Unifying ViewAbraham Imohiosen, Jan Peters Joe Watson2020≈ 77%
- Active Inference with People: a general approach to real-time adaptive experimentsNori Jacoby, Peter Harrison Lucas Gautheron2026≈ 77%
- ≈ 77%
- Active inference for action-unaware agentsKeisuke Suzuki, Ryota Kanai, Manuel Baltieri Filippo Torresan2025≈ 76%
- Active inference: demystified and comparedPhilip J. Ball, Thomas Parr, Karl J. Friston Noor Sajid2021≈ 76%
- Active Inference for Autonomous Decision-Making with Contextual Multi-Armed BanditsShohei Wakayama and Nisar Ahmed2023≈ 76%
- ≈ 76%
- ≈ 76%
- Active Inference: A Process Theoryin corpus2017≈ 73%
- ≈ 72%
- ≈ 71%
- ≈ 69%
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetsin corpus2023≈ 68%
- Model Alignment Searchin corpus2025≈ 68%
- ≈ 68%
- Simulators — LessWrongin corpus≈ 68%
- When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Modelsin corpus2025≈ 68%
- ≈ 68%
- Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiesin corpus2023≈ 67%
- Interpreting Language Model Parametersin corpus2026≈ 67%
Similar preprints — Semantic Scholar
Cited by (4)
- Active Inference, Curiosity and Insight
Minimizing expected variational free energy under a discrete-state Markov decision process generative model is sufficient to produce curiosity, epistemic learning, and insight without any additional m
- Active inference: demystified and compared
Active inference agents operating under expected free energy minimization achieve 98.90 [98.00, 99.79] average score in a non-stationary FrozenLake OpenAI gym environment, compared to 64.39 [60.33, 68
- Active Inference: A Process Theory
A single variational principle—minimizing variational free energy via gradient descent on a Markov decision process (MDP) generative model—is sufficient to derive neuronal dynamics that reproduce, wit
- Active inference on discrete state-spaces: a synthesis
Active inference on discrete state-spaces, formalized as partially observable Markov decision processes (POMDPs) with likelihood matrix A, transition matrix B, and prior D, unifies perception, plannin