Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences. Although many existing robotics studies use a forward model framework, there are generalization issues with high degrees of freedom. The current study shows that the predictive coding (PC) and active inference (AIF) frameworks, which employ a generative model, can develop better generalization by learning a prior distribution in a low dimensional latent state space representing probabilistic structures extracted from well habituated sensory-motor trajectories. In our proposed model, learning is carried out by inferring optimal latent variables as well as synaptic weights for maximizing the evidence lower bound, while goal-directed planning is accomplished by inferring latent variables for maximizing the estimated lower bound. Our proposed model was evaluated with both simple and complex robotic tasks in simulation, which demonstrated sufficient generalization in learning with limited training data by setting an intermediate value for a regularization coefficient. Furthermore, comparative simulation results show that the proposed model outperforms a conventional forward model in goal-directed planning, due to the learned prior confining the search of motor plans within the range of habituated trajectories.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rao, R. P. N., & Ballard, D. H. (1999) · Nature Neuroscience · doi:10.1038/4580 · Cited by 5,483 · cited 2×
“The first is by adapting belief or intention represented by the internal state of the generative model so that the reconstruction error can be minimized [34, 12, 21, 10].”
BackgroundInternal models for motor control and trajectory planning.
Kawato, M. (1999) · Current Opinion in Neurobiology · doi:10.1016/s0959-4388(99)00028-8 · Cited by 2,685 · cited 1×
“nd action are effectively two sides of the same coin in enactive cognition. Originally, the idea of an internal model for sensory-motor systems was investigated in the study of the forward model (FM) [29, 25, 24] (see Figure 1a). Although both FM and PC can predict the next latent state and associated sensory inputs,…”
BackgroundForward Models for Physiological Motor Control
Miall, R. C., & Wolpert, D. M. (1996) · Neural Networks · doi:10.1016/s0893-6080(96)00035-4 · Cited by 2,260
Hohwy, J. (2013) · doi:10.1093/acprof:oso/9780199682737.001.0001 · Cited by 1,914
Hierarchical Bayesian inference in the visual cortex
Lee, T. S., & Mumford, D. (2003) · Journal of the Optical Society of America A · doi:10.1364/josaa.20.001434 · Cited by 1,473 · cited 1×
“proposes a novel model for goal-directed plan generation referred to as goal-directed latent variable inference (GLean), based on learning by leveraging two related frameworks, predictive coding (PC) [34, 38, 28, 12, 21, 10, 13] and active inference (AIF) [15, 16, 17, 5, 33, 31]. In particular, we attempt to show that…”
BackgroundA free energy principle for the brain
Friston, K., Kilner, J., & Harrison, L. (2006) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2006.10.001 · Cited by 1,369
Surfing Uncertainty: Prediction, Action, and the Embodied Mind
Clark, A. (2016) · doi:10.1093/acprof:oso/9780190217013.001.0001 · Cited by 1,358
Intrinsic Motivation Systems for Autonomous Mental Development
Oudeyer, P.-Y., Kaplan, F., & Hafner, V. V. (2007) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2006.890271 · Cited by 1,126
Action and behavior: a free-energy formulation
Friston, K. J., Daunizeau, J., Kilner, J., & Kiebel, S. J. (2010) · Biological Cybernetics · doi:10.1007/s00422-010-0364-z · Cited by 866 · cited 11×
“In this current paper, we propose a further development of the aforementioned model using the framework of PC and AIF to tackle the issue of learning-based goal-directed motor planning by expanding upon the variational Bayes approach.”
BackgroundInfluentialLearning Latent Dynamics for Planning from Pixels
Hafner, D., Lillicrap, T., Fischer, I., Villegas, R., Ha, D., Lee, H., & Davidson, J. (2018) · arXiv · doi:10.48550/arxiv.1811.04551 · Cited by 708
Cited by
Predictive processing in cognitive robotics: A review
Ciria, A., Schillaci, G., Pezzulo, G., Hafner, V. V., & Lara, B. (2021) · Neural Computation · doi:10.1162/neco_a_01383 · Cited by 51
“In more recent works (e.g. (Matsumoto and Tani, 2020; Jung et al., 2019)), authors use explicitly variational inference.”
BackgroundNeural dynamics under active inference: plausibility and efficiency of information processing
Da Costa, L., Parr, T., Sengupta, B., & Friston, K. (2021) · Entropy · doi:10.3390/e23040454 · Cited by 38
Hierarchical generative modelling for autonomous robots
Yuan, K., Sajid, N., Friston, K., & Li, Z. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00752-z · Cited by 23
“This proposal inherits from hierarchical functional organization of human motor control and ensuing planning as inference 21,23,24 , active inference 25–28 or control as inference 29,30 .”
Metadata
- Authors
- Matsumoto, T., & Tani, J.
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2020-05-18
- Volume
- 22
- Issue
- 5
- Pages
- 564
- ISSN
- 1099-4300 (ISSN-L)
- OpenAlex
- W3025794913
- Cited by
- 36
- References
- 19
- FWCI
- 3.38
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network. https://app.cochat.ai/papers/10.3390/e22050564
- The paper
- Matsumoto, T., & Tani, J. (2020). Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network. Entropy. https://doi.org/10.3390/e22050564
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.