pith. sign in

arxiv: 2606.04935 · v3 · pith:FP76M6LCnew · submitted 2026-06-03 · 💻 cs.AI

What Type of Inference is Active Inference?

Wouter W. L. Nuijten , Mykola Lukashchuk , Thijs van de Laar , Bert de Vries This is my paper

Pith reviewed 2026-06-28 06:43 UTC · model grok-4.3

classification 💻 cs.AI
keywords active inferenceexpected free energyvariational free energyepistemic priorspolicy optimizationmessage passingplanning correctionsgrid world
0
0 comments X

The pith

Active inference requires both entropy corrections and a planning correction to achieve full expected free energy minimization.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that expected free energy minimization can be recast as variational free energy minimization on a generative model with added epistemic priors. This augmented variational free energy can be rewritten as the variational free energy of the predictive model plus explicit entropy-correction terms. Proper EFE-based planning then requires an additional planning correction that converts marginal inference into policy optimization. The resulting decomposition supplies a complete variational account of EFE planning and supports a concrete message-passing implementation. Grid-world experiments confirm that agents using both corrections outperform versions that omit either one.

Core claim

Expected free energy minimization equals variational free energy minimization on a generative model augmented with epistemic priors; the augmented variational free energy decomposes into the predictive model's variational free energy plus explicit entropy-correction terms; full EFE-based planning further requires a planning correction that turns marginal inference into policy optimization, yielding a complete variational characterization together with an associated message-passing scheme.

What carries the argument

The decomposition of the variational free energy of the epistemically augmented model into predictive variational free energy plus explicit entropy-correction terms, together with the planning correction that converts marginal inference into policy optimization.

If this is right

  • The variational free energy of the augmented model equals the predictive model's variational free energy plus explicit entropy-correction terms.
  • Full EFE-based planning combines the epistemic corrections with a planning correction.
  • The decomposition yields a message-passing scheme for EFE-based planning and simpler ablations.
  • In grid-world tasks the full combination outperforms ablations that omit either correction.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The explicit separation of corrections may allow implementers to add or remove information-seeking behavior without rewriting the entire planner.
  • The same structure could be used to derive message-passing updates for other free-energy objectives that mix goal-directed and epistemic terms.
  • Because the corrections are stated in terms of standard variational quantities, they may transfer to continuous or high-dimensional state spaces where exact marginals are unavailable.

Load-bearing premise

That expected free energy minimization can be expressed as variational free energy minimization on a generative model augmented with epistemic priors.

What would settle it

An ablation experiment in which an agent performs full EFE planning without the planning correction and still matches the performance and policy distribution of the complete version.

Figures

Figures reproduced from arXiv: 2606.04935 by Bert de Vries, Mykola Lukashchuk, Thijs van de Laar, Wouter W. L. Nuijten.

Figure 1
Figure 1. Figure 1: Forney factor graph for the generative model [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: A Forney-style factor graph representing the factorization [PITH_FULL_IMAGE:figures/full_fig_p018_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Wumpus World trajectories for all five methods on configuration [PITH_FULL_IMAGE:figures/full_fig_p035_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Wumpus World trajectories on configuration [PITH_FULL_IMAGE:figures/full_fig_p035_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Convergence rate (color) and median iterations to convergence (in parentheses) for each method and damping [PITH_FULL_IMAGE:figures/full_fig_p036_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: VFE traces on Frozen Lake for all methods at their best damping (seed-averaged with [PITH_FULL_IMAGE:figures/full_fig_p037_7.png] view at source ↗
read the original abstract

Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior. Recent work showed that EFE minimization can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors. We prove that the VFE of the augmented model can be rewritten as the VFE of the predictive model plus explicit entropy-correction terms, making the EFE contribution transparent. We then show that proper EFE-based planning requires combining these epistemic corrections with a planning correction that turns marginal inference into policy optimization, yielding a full variational characterization of EFE-based planning. This clarifies which corrections are needed for cross-entropy planning and for full EFE-based planning. The same entropy-corrected formulation leads to a detailed message-passing scheme for EFE-based planning together with simpler ablations. Experiments on three grid-world environments show that full EFE-based planning outperforms ablations that omit either the planning correction or the epistemic corrections.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The paper claims that Expected Free Energy (EFE) minimization can be expressed as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors. It proves that the VFE on the augmented model equals the VFE on the predictive model plus explicit entropy-correction terms. It further demonstrates that EFE-based planning requires an additional planning correction to transform marginal inference into policy optimization, providing a complete variational characterization. This leads to a message-passing scheme for EFE-based planning and ablations. Experiments in three grid-world environments show that the full EFE-based planning outperforms ablations missing either the planning or epistemic corrections.

Significance. If the results hold, this work provides a significant clarification on the nature of inference in active inference by decomposing EFE into standard VFE plus specific corrections. The explicit entropy corrections and the planning correction are useful for understanding and implementing EFE-based planning. Credit is given for deriving the message-passing scheme from the corrected formulation and for the ablation studies in grid-worlds that support the necessity of both corrections. This could advance the field by making the contributions of different terms transparent.

minor comments (2)
  1. [Abstract] The abstract mentions 'cross-entropy planning' without a brief definition or reference, which may confuse readers unfamiliar with the term.
  2. The paper would benefit from including the specific names or characteristics of the three grid-world environments in the abstract or early introduction for better context.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive and accurate summary of our work, the recognition of its significance, and the recommendation for minor revision. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper starts from standard VFE and EFE definitions (as stated in the abstract), references recent work only for the initial augmented-model rewriting, and then derives explicit entropy-correction terms plus a planning correction that converts marginal inference to policy optimization. These steps are presented as independent proofs and rewritings that produce a message-passing scheme and ablation comparisons; no load-bearing step reduces by construction to a fitted input, self-citation chain, or renamed ansatz. The central claim therefore remains self-contained against the stated definitions.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The work rests on standard variational inference assumptions and the definition of the augmented model with epistemic priors; no free parameters, new entities, or ad-hoc axioms are introduced in the abstract.

axioms (1)
  • standard math Standard variational inference assumptions that a variational distribution approximates the true posterior and that free-energy minimization yields useful inference.
    The rewriting begins from VFE minimization on the augmented model.

pith-pipeline@v0.9.1-grok · 5701 in / 1187 out tokens · 38803 ms · 2026-06-28T06:43:43.941532+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 182 canonical work pages · 22 internal anchors

  1. [1]

    Adamiat, Sepideh and Kouw, Wouter M. and. Message. Active. doi:10.1007/978-3-031-77138-5_14 , abstract =

    work page doi:10.1007/978-3-031-77138-5_14

  2. [2]

    and Shipp, Stewart and Friston, Karl J

    Adams, Rick A. and Shipp, Stewart and Friston, Karl J. , year = 2013, journal =. Predictions Not Commands: Active Inference in the Motor System , shorttitle =. doi:10.1007/s00429-012-0475-5 , url =

    work page doi:10.1007/s00429-012-0475-5 2013

  3. [3]

    and Murphy, Kevin , year = 2018, month = jul, pages =

    Alemi, Alexander and Poole, Ben and Fischer, Ian and Dillon, Joshua and Saurous, Rif A. and Murphy, Kevin , year = 2018, month = jul, pages =. Fixing a. Proceedings of the 35th

    2018

  4. [4]

    Computationally Efficient Convolved Multiple Output

    Alvarez, Mauricio A and Lawrence, Neil D , year = 2011, journal =. Computationally Efficient Convolved Multiple Output

    2011

  5. [5]

    and Rosasco, Lorenzo and Lawrence, Neil D

    Alvarez, Mauricio A. and Rosasco, Lorenzo and Lawrence, Neil D. , year = 2012, month = apr, number =. Kernels for. arXiv , langid =:1106.6251 , primaryclass =

    Pith/arXiv arXiv 2012

  6. [6]

    , year = 2012, month = jun, pages =

    Anandkumar, Animashree and Hsu, Daniel and Kakade, Sham M. , year = 2012, month = jun, pages =. A. Proceedings of the 25th

    2012

  7. [7]

    Anil Meera, Ajith and Lanillos, Pablo , editor =. Towards. Active. doi:10.1007/978-3-031-47958-8_3 , abstract =

    work page doi:10.1007/978-3-031-47958-8_3

  8. [8]

    Biosystems , volume =

    Natural Hierarchy Emerges from Energy Dispersal , author =. Biosystems , volume =. doi:10.1016/j.biosystems.2008.10.008 , url =

    work page doi:10.1016/j.biosystems.2008.10.008 2008

  9. [9]

    Declarative

    Antoy, Sergio and Hanus, Michael , editor =. Declarative. Logic. doi:10.1007/11680093_2 , abstract =

    work page doi:10.1007/11680093_2

  10. [10]

    and Nouri, Ali and Wingate, David , year = 2009, month = jun, series =

    Asmuth, John and Li, Lihong and Littman, Michael L. and Nouri, Ali and Wingate, David , year = 2009, month = jun, series =. A. Proceedings of the

    2009

  11. [11]

    A Bayesian Sampling Approach to Exploration in Reinforcement Learning

    Asmuth, John and Li, Lihong and Littman, Michael L. and Nouri, Ali and Wingate, David , year = 2012, month = may, number =. A. doi:10.48550/arXiv.1205.2664 , url =. arXiv , keywords =:1205.2664 , primaryclass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1205.2664 2012

  12. [12]

    Planning by Probabilistic Inference , booktitle =

    Attias, Hagai , year = 2003, pages =. Planning by Probabilistic Inference , booktitle =

    2003

  13. [13]

    Reinforcement

    Azizzadenesheli, Kamyar and Lazaric, Alessandro and Anandkumar, Animashree , year = 2016, month = jun, pages =. Reinforcement. Conference on

    2016

  14. [14]

    Reactive

    Bagaev, Dmitry and. Reactive. doi:10.48550/arXiv.2112.13251 , url =. arXiv , keywords =:2112.13251 , primaryclass =

    work page doi:10.48550/arxiv.2112.13251

  15. [15]

    Reactive

    Bagaev, Dmitry and De Vries, Bert , editor =. Reactive. Scientific Programming , volume =. doi:10.1155/2023/6601690 , url =

    work page doi:10.1155/2023/6601690 2023

  16. [16]

    Software Impacts , volume =

    Bagaev, Dmitry and. Software Impacts , volume =. doi:10.1016/j.simpa.2022.100299 , url =

    work page doi:10.1016/j.simpa.2022.100299 2022

  17. [17]

    Rocket.Jl:

    Bagaev, Dmitry , year = 2020, url =. Rocket.Jl:

    2020

  18. [18]

    doi:10.21105/joss.05161 , url =

    Bagaev, Dmitry and Podusenko, Albert and de Vries, Bert , year = 2023, month = apr, journal =. doi:10.21105/joss.05161 , url =

    work page doi:10.21105/joss.05161 2023

  19. [19]

    ACM Computing Surveys (CSUR) , volume =

    A Survey on Reactive Programming , author =. ACM Computing Surveys (CSUR) , volume =. doi:10.1145/2501654.2501666 , url =

    work page doi:10.1145/2501654.2501666

  20. [20]

    and Simpson, Daniel and Rue, H

    Bakka, Haakon and Vanhatalo, Jarno and Illian, Janine B. and Simpson, Daniel and Rue, H. Non-Stationary. Spatial Statistics , volume =. doi:10.1016/j.spasta.2019.01.002 , url =

    work page doi:10.1016/j.spasta.2019.01.002 2019

  21. [21]

    and Daulton, Samuel and Letham, Benjamin and Wilson, Andrew Gordon and Bakshy, Eytan , year = 2020, month = dec, series =

    Balandat, Maximilian and Karrer, Brian and Jiang, Daniel R. and Daulton, Samuel and Letham, Benjamin and Wilson, Andrew Gordon and Bakshy, Eytan , year = 2020, month = dec, series =. Proceedings of the 34th

    2020

  22. [22]

    arXiv , keywords =:2111.10530 , primaryclass =

    Kalman Filters as the Steady-State Solution of Gradient Descent on Variational Free Energy , author =. arXiv , keywords =:2111.10530 , primaryclass =

    arXiv

  23. [23]

    Reactive Probabilistic Programming , booktitle =

    Baudart, Guillaume and Mandel, Louis and Atkinson, Eric and Sherman, Benjamin and Pouzet, Marc and Carbin, Michael , year = 2020, month = jun, series =. Reactive Probabilistic Programming , booktitle =. doi:10.1145/3385412.3386009 , url =

    work page doi:10.1145/3385412.3386009 2020

  24. [24]

    Beck, Jeff and Ramstead, Maxwell J. D. , year = 2025, month = feb, number =. Dynamic. doi:10.48550/arXiv.2502.21217 , url =. arXiv , keywords =:2502.21217 , primaryclass =

    work page doi:10.48550/arxiv.2502.21217 2025

  25. [25]

    Bellman, Richard , year = 1966, journal =. Dynamic. 1719695 , eprinttype =

    1966

  26. [26]

    Bulletin of the American Mathematical Society , volume =

    The Theory of Dynamic Programming , author =. Bulletin of the American Mathematical Society , volume =. doi:10.1090/S0002-9904-1954-09848-8 , url =

    work page doi:10.1090/s0002-9904-1954-09848-8 1954

  27. [27]

    Robustness in Identification and Control , author =

    Robust Model Predictive Control:. Robustness in Identification and Control , author =. doi:10.1007/BFb0109870 , abstract =

    work page doi:10.1007/bfb0109870

  28. [28]

    Multidimensional Binary Search Trees Used for Associative Searching , author =. Commun. ACM , volume =. doi:10.1145/361002.361007 , url =

    work page doi:10.1145/361002.361007

  29. [29]

    Dynamic Programming and Optimal Control:

    Bertsekas, Dimitri , year = 2012, volume =. Dynamic Programming and Optimal Control:

    2012

  30. [30]

    Julia: A Fresh Approach to Numerical Computing

    Bezanson, Jeff and Edelman, Alan and Karpinski, Stefan and Shah, Viral B. , year = 2015, month = jul, number =. Julia:. doi:10.48550/arXiv.1411.1607 , url =. arXiv , keywords =:1411.1607 , primaryclass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1411.1607 2015

  31. [31]

    Bingham, Eli and Chen, Jonathan P and Jankowiak, Martin and Obermeyer, Fritz and Pradhan, Neeraj and Karaletsos, Theofanis and Singh, Rohit and Szerlip, Paul and Horsfall, Paul and Goodman, Noah D , year = 2019, journal =. Pyro:

    2019

  32. [32]

    Pattern Recognition and Machine Learning , author =

  33. [33]

    , year = 2011, month = dec, journal =

    Blackmore, Lars and Ono, Masahiro and Williams, Brian C. , year = 2011, month = dec, journal =. Chance-. doi:10.1109/TRO.2011.2161160 , url =

    work page doi:10.1109/tro.2011.2161160 2011

  34. [34]

    and Jordan, Michael I

    Blei, David M. and Jordan, Michael I. , year = 2006, month = mar, journal =. Variational Inference for. doi:10.1214/06-BA104 , url =

    work page doi:10.1214/06-ba104 2006

  35. [35]

    and Kucukelbir, Alp and McAuliffe, Jon D

    Blei, David M. and Kucukelbir, Alp and McAuliffe, Jon D. , year = 2017, month = apr, journal =. Variational. doi:10.1080/01621459.2017.1285773 , url =

    work page doi:10.1080/01621459.2017.1285773 2017

  36. [36]

    Bayesian

    Bliznyuk, Nikolay and Ruppert, David and Shoemaker, Christine and Regis, Rommel and Wild, Stefan and Mugunthan, Pradeep , year = 2008, month = jun, journal =. Bayesian. doi:10.1198/106186008X320681 , url =

    work page doi:10.1198/106186008x320681 2008

  37. [37]

    Biosystems Engineering , volume =

    Minimising the Non-Working Distance Travelled by Machines Operating in a Headland Field Pattern , author =. Biosystems Engineering , volume =. doi:10.1016/j.biosystemseng.2008.06.008 , url =

    work page doi:10.1016/j.biosystemseng.2008.06.008 2008

  38. [38]

    Bolin, David and Lindgren, Finn , year = 2011, journal =. Spatial. 23024839 , eprinttype =

    2011

  39. [39]

    Artificial Intelligence , volume =

    Planning as Heuristic Search , author =. Artificial Intelligence , volume =. doi:10.1016/S0004-3702(01)00108-4 , url =

    work page doi:10.1016/s0004-3702(01)00108-4

  40. [40]

    Multi-Task

    Bonilla, Edwin V and Chai, Kian and Williams, Christopher , year = 2007, volume =. Multi-Task. Advances in

    2007

  41. [41]

    The International Journal of Robotics Research , volume =

    Closing the Learning-Planning Loop with Predictive State Representations , author =. The International Journal of Robotics Research , volume =. doi:10.1177/0278364911404092 , url =

    work page doi:10.1177/0278364911404092

  42. [42]

    Mat\'ern

    Borovitskiy, Viacheslav and Terenin, Alexander and Mostowsky, Peter and Deisenroth, Marc Peter , year = 2020, month = dec, series =. Mat\'ern. Proceedings of the 34th

    2020

  43. [43]

    Trends in Cognitive Sciences , volume =

    Planning as Inference , author =. Trends in Cognitive Sciences , volume =. doi:10.1016/j.tics.2012.08.006 , url =

    work page doi:10.1016/j.tics.2012.08.006 2012

  44. [44]

    Generating Sentences from a Continuous Space , booktitle =

    Bowman, Samuel and Vilnis, Luke and Vinyals, Oriol and Dai, Andrew and Jozefowicz, Rafal and Bengio, Samy , year = 2016, pages =. Generating Sentences from a Continuous Space , booktitle =

    2016

  45. [45]

    Bradbury, James and Frostig, Roy and Hawkins, Peter and Johnson, Matthew James and Leary, Chris and Maclaurin, Dougal and Necula, George and Paszke, Adam and VanderPlas, Jake and

  46. [46]

    OpenAI Gym

    Brockman, Greg and Cheung, Vicki and Pettersson, Ludwig and Schneider, Jonas and Schulman, John and Tang, Jie and Zaremba, Wojciech , year = 2016, month = jun, number =. doi:10.48550/arXiv.1606.01540 , url =. arXiv , keywords =:1606.01540 , primaryclass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1606.01540 2016

  47. [47]

    Scalable

    Bruinsma, Wessel and Perim, Eric and Tebbutt, William and Hosking, Scott and Solin, Arno and Turner, Richard , year = 2020, month = nov, pages =. Scalable. Proceedings of the 37th

    2020

  48. [48]

    and Kim, Chang Sub and McGregor, Simon and Seth, Anil K

    Buckley, Christopher L. and Kim, Chang Sub and McGregor, Simon and Seth, Anil K. , year = 2017, month = dec, journal =. The Free Energy Principle for Action and Perception:. doi:10.1016/j.jmp.2017.09.004 , url =

    work page doi:10.1016/j.jmp.2017.09.004 2017

  49. [49]

    and Nguyen, Cuong V

    Bui, Thang D. and Nguyen, Cuong V. and Turner, Richard E. , year = 2017, month = dec, series =. Streaming Sparse. Proceedings of the 31st

    2017

  50. [50]

    Finding the Outliers in Scanpath Data , booktitle =

    Burch, Michael and Kumar, Ayush and Mueller, Klaus and Kervezee, Titus and Nuijten, Wouter and Oostenbach, Rens and Peeters, Lucas and Smit, Gijs , year = 2019, month = jun, series =. Finding the Outliers in Scanpath Data , booktitle =. doi:10.1145/3317958.3318225 , url =

    work page doi:10.1145/3317958.3318225 2019

  51. [51]

    and Lee, Daniel and Goodrich, Ben and Betancourt, Michael and Brubaker, Marcus and Guo, Jiqiang and Li, Peter and Riddell, Allen , year = 2017, journal =

    Carpenter, Bob and Gelman, Andrew and Hoffman, Matthew D. and Lee, Daniel and Goodrich, Ben and Betancourt, Michael and Brubaker, Marcus and Guo, Jiqiang and Li, Peter and Riddell, Allen , year = 2017, journal =. doi:10.18637/jss.v076.i01 , url =

    work page doi:10.18637/jss.v076.i01 2017

  52. [52]

    Stochastic Versions of the Em Algorithm: An Experimental Study in the Mixture Case , shorttitle =

    Celeux,. Stochastic Versions of the Em Algorithm: An Experimental Study in the Mixture Case , shorttitle =. Journal of Statistical Computation and Simulation , volume =. doi:10.1080/00949659608811772 , url =

    work page doi:10.1080/00949659608811772

  53. [53]

    Branching

    Champion, Th. Branching. Neural Networks , volume =. doi:10.1016/j.neunet.2022.03.036 , url =

    work page doi:10.1016/j.neunet.2022.03.036 2022

  54. [54]

    Chang, Huiwen and Zhang, Han and Barber, Jarred and Maschinot, A. J. and Lezama, Jose and Jiang, Lu and Yang, Ming-Hsuan and Murphy, Kevin and Freeman, William T. and Rubinstein, Michael and Li, Yuanzhen and Krishnan, Dilip , year = 2023, month = jan, number =. Muse:. doi:10.48550/arXiv.2301.00704 , url =. arXiv , keywords =:2301.00704 , primaryclass =

    work page doi:10.48550/arxiv.2301.00704 2023

  55. [55]

    Chen, Fan and Wang, Huan and Xiong, Caiming and Mei, Song and Bai, Yu , year = 2023, month = jul, pages =. Lower. Proceedings of the 40th

    2023

  56. [56]

    Physical Review E , volume =

    Loop Calculus in Statistical Physics and Information Science , author =. Physical Review E , volume =. doi:10.1103/PhysRevE.73.065102 , url =

    work page doi:10.1103/physreve.73.065102

  57. [57]

    Advances in Neural Information Processing Systems , volume =

    Minigrid & Miniworld:. Advances in Neural Information Processing Systems , volume =

  58. [58]

    Temporal

    Corenflos, Adrien and Zhao, Zheng and S. Temporal. 2022 25th. doi:10.23919/FUSION49751.2022.9841306 , url =

    work page doi:10.23919/fusion49751.2022.9841306 2022

  59. [59]

    Introduction to Algorithms , author =

  60. [60]

    BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models

    Coscia, Dario and L. doi:10.48550/arXiv.2605.08110 , url =. arXiv , keywords =:2605.08110 , primaryclass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2605.08110

  61. [61]

    International

    Cox, Marco and. International

  62. [62]

    American journal of physics , volume =

    Probability, Frequency and Reasonable Expectation , author =. American journal of physics , volume =

  63. [63]

    and Ramaker, B

    Cutler, Richard R. and Ramaker, B. L. , year = 1979, journal =. Dynamic

    1979

  64. [64]

    Active Inference on Discrete State-Spaces:

    Da Costa, Lancelot and Parr, Thomas and Sajid, Noor and Veselic, Sebastijan and Neacsu, Victorita and Friston, Karl , year = 2020, month = dec, journal =. Active Inference on Discrete State-Spaces:. doi:10.1016/j.jmp.2020.102447 , url =

    work page doi:10.1016/j.jmp.2020.102447 2020

  65. [65]

    Da Costa, Lancelot and Tenka, Samuel and Zhao, Dominic and Sajid, Noor , year = 2024, month = jan, number =. Active. doi:10.48550/arXiv.2401.12917 , url =. arXiv , keywords =:2401.12917 , primaryclass =

    work page doi:10.48550/arxiv.2401.12917 2024

  66. [66]

    doi:10.5194/essd-15-317-2023 , url =

    Earth System Science Data , volume =. doi:10.5194/essd-15-317-2023 , url =

    work page doi:10.5194/essd-15-317-2023 2023

  67. [67]

    IEEE Transactions on Geoscience and Remote Sensing , volume =

    Bayesian. IEEE Transactions on Geoscience and Remote Sensing , volume =. doi:10.1109/TGRS.2024.3434443 , url =

    work page doi:10.1109/tgrs.2024.3434443 2024

  68. [68]

    Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective

    Daulton, Samuel and Balandat, Maximilian and Bakshy, Eytan , year = 2020, month = dec, series =. Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective. Proceedings of the 34th

    2020

  69. [69]

    Parallel

    Daulton, Samuel and Balandat, Maximilian and Bakshy, Eytan , year = 2021, month = dec, series =. Parallel. Proceedings of the 35th

    2021

  70. [70]

    , year = 2007, month = jun, pages =

    Dauwels, J. , year = 2007, month = jun, pages =. On. doi:10.1109/ISIT.2007.4557602 , abstract =

    work page doi:10.1109/isit.2007.4557602 2007

  71. [71]

    doi:10.1109/MMAR.2012.6347921 , url =

    Consistent Control Hierarchies with Top Layers Represented by Timed Event Graphs , booktitle =. doi:10.1109/MMAR.2012.6347921 , url =

    work page doi:10.1109/mmar.2012.6347921 2012

  72. [72]

    Entropy , volume =

    Spatial and. Entropy , volume =. doi:10.3390/e26010083 , url =

    work page doi:10.3390/e26010083

  73. [73]

    De Vries, Bert , year = 2026, month = mar, number =. Active. doi:10.48550/arXiv.2603.20927 , url =. arXiv , keywords =:2603.20927 , primaryclass =

    work page doi:10.48550/arxiv.2603.20927 2026

  74. [74]

    Expected

    De Vries, Bert and Nuijten, Wouter and. Expected. doi:10.48550/arXiv.2504.14898 , url =. arXiv , keywords =:2504.14898 , primaryclass =

    work page doi:10.48550/arxiv.2504.14898

  75. [75]

    Journal of neural engineering , volume =

    The Neural Optimal Control Hierarchy for Motor Control , author =. Journal of neural engineering , volume =

  76. [76]

    TensorFlow Distributions

    Dillon, Joshua V. and Langmore, Ian and Tran, Dustin and Brevdo, Eugene and Vasudevan, Srinivas and Moore, Dave and Patton, Brian and Alemi, Alex and Hoffman, Matt and Saurous, Rif A. , year = 2017, month = nov, number =. doi:10.48550/arXiv.1711.10604 , url =. arXiv , keywords =:1711.10604 , primaryclass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1711.10604 2017

  77. [77]

    IJCAI : proceedings of the conference , volume =

    Hidden. IJCAI : proceedings of the conference , volume =

  78. [78]

    Stochastic

    Dritsas, Ioannis , year = 2011, month = feb, publisher =. Stochastic

    2011

  79. [79]

    and Del Bello, U

    Drusch, M. and Del Bello, U. and Carlier, S. and Colin, O. and Fernandez, V. and Gascon, F. and Hoersch, B. and Isola, C. and Laberinti, P. and Martimort, P. and Meygret, A. and Spoto, F. and Sy, O. and Marchese, F. and Bargellini, P. , year = 2012, month = may, journal =. Sentinel-2:. doi:10.1016/j.rse.2011.11.026 , url =

    work page doi:10.1016/j.rse.2011.11.026 2012

  80. [80]

    Duane, Simon and Kennedy, A. D. and Pendleton, Brian J. and Roweth, Duncan , year = 1987, month = sep, journal =. Hybrid. doi:10.1016/0370-2693(87)91197-X , url =

    work page doi:10.1016/0370-2693(87)91197-x 1987

Showing first 80 references.