paper:doi-10-1007-s00422-012-0512-8Active inference and agency: optimal control without cost functions
Original abstract (expand)
This paper describes a variational free-energy formulation of (partially observable) Markov decision problems in decision making under uncertainty. We show that optimal control can be cast as active inference. In active inference, both action and posterior beliefs about hidden states minimise a free energy bound on the negative log-likelihood of observed states, under a generative model. In this setting, reward or cost functions are absorbed into prior beliefs about state transitions and terminal states. Effectively, this converts optimal control into a pure inference problem, enabling the application of standard Bayesian filtering techniques. We then consider optimal trajectories that rest on posterior beliefs about hidden states in the future. Crucially, this entails modelling control as a hidden state that endows the generative model with a representation of agency. This leads to a distinction between models with and without inference on hidden control states; namely, agency-free and agency-based models, respectively.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Active Inference or Control as Inference? A Unifying ViewAbraham Imohiosen, Jan Peters Joe Watson2020≈ 80%
- ≈ 77%
- Deriving time-averaged active inference from control principlesJordan Theriault, Jan-Willem van de Meent, Lisa Feldman Barrett, Karen Quigley Eli Sennesh2022≈ 76%
- Active inference and artificial reasoningLancelot Da Costa, Alexander Tschantz, Conor Heins, Christopher Buckley, Tim Verbelen, Thomas Parr Karl Friston2025≈ 76%
- On the Relationship Between Active Inference and Control as InferenceAlexander Tschantz, Anil K Seth, Christopher L Buckley Beren Millidge2020≈ 76%
- Modeling motor control in continuous-time Active Inference: a surveyFederico Maggiore, Antonella Maselli, Francesco Donnarumma, Domenico Maisto, Francesco Mannella, Ivilin Peev Stoianov and Giovanni Pezzulo Matteo Priorelli2024≈ 76%
- Active inference for action-unaware agentsKeisuke Suzuki, Ryota Kanai, Manuel Baltieri Filippo Torresan2025≈ 76%
- Active inference, Bayesian optimal design, and expected utilityLancelot Da Costa, Thomas Parr, Karl Friston Noor Sajid2021≈ 76%
- ≈ 76%
- Active Inference: A method for Phenotyping Agency in AI systems?Philip Wilson and Axel Constant and Mahault Albarracin and Nicol\'as Hinrichs and Jasmine Moore and Daniel Polani and Karl Friston2026≈ 76%
- Reward Maximisation through Discrete Active InferenceNoor Sajid, Thomas Parr, Karl Friston, Ryan Smith Lancelot Da Costa2022≈ 76%
- ≈ 75%
- Active Inference in Robotics and Artificial Agents: Survey and ChallengesCristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani Pablo Lanillos2021≈ 75%
- Active inference: demystified and comparedPhilip J. Ball, Thomas Parr, Karl J. Friston Noor Sajid2021≈ 75%
- ≈ 75%
- Active inference: demystified and comparedin corpus2021≈ 73%
- ≈ 71%
- Active Inference: A Process Theoryin corpus2017≈ 70%
- ≈ 69%
- Active Inference, Curiosity and Insightin corpus2017≈ 68%
- ≈ 67%
- ≈ 67%
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligencein corpus2026≈ 66%
- Simulators — LessWrongin corpus≈ 65%
- ≈ 65%
- ≈ 64%
- ≈ 63%
- ≈ 63%
- Learning without neurons in physical systemsin corpus2022≈ 63%
- Contemplative Agentin corpus2025≈ 63%
Similar preprints — Semantic Scholar
Cited by (4)
- 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
- The computational boundary of a 'self': developmental bioelectricity drives multicellularity and scale-free cognition
Scale-Free Cognition, the framework introduced here, proposes that any coherent Self is demarcated by a 'cognitive light cone'—a spatio-temporal boundary of events a system can measure, model, and att
- 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
- Brains and where else? Mapping theories of consciousness to unconventional embodiments
Rouleau and Levin's 2026 analysis in *Philosophical Transactions of the Royal Society A* (384, issue 2320) demonstrates that the functional and operational principles underlying most contemporary theo