Learning and exploration in action-perception loops
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Discovering the structure underlying observed data is a recurring problem in machine learning with important applications in neuroscience. It is also a primary function of the brain. When data can be actively collected in the context of a closed action-perception loop, behavior becomes a critical determinant of learning efficiency. Psychologists studying exploration and curiosity in humans and animals have long argued that learning itself is a primary motivator of behavior. However, the theoretical basis of learning-driven behavior is not well understood. Previous computational studies of behavior have largely focused on the control problem of maximizing acquisition of rewards and have treated learning the structure of data as a secondary objective. Here, we study exploration in the absence of external reward feedback. Instead, we take the quality of an agent's learned internal model to be the primary objective. In a simple probabilistic framework, we derive a Bayesian estimate for the amount of information about the environment an agent can expect to receive by taking an action, a measure we term the predicted information gain (PIG). We develop exploration strategies that approximately maximize PIG. One strategy based on value-iteration consistently learns faster than previously developed reward-free exploration strategies across a diverse range of environments. Psychologists believe the evolutionary advantage of learning-driven exploration lies in the generalized utility of an accurate internal model. Consistent with this hypothesis, we demonstrate that agents which learn more efficiently during exploration are later better able to accomplish a range of goal-directed tasks. We will conclude by discussing how our work elucidates the explorative behaviors of animals and humans, its relationship to other computational models of behavior, and its potential application to experimental design, such as in closed-loop neurophysiology studies.
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
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
Optimal foraging, the marginal value theorem
Charnov, E. L. (1976) · Theoretical Population Biology · doi:10.1016/0040-5809(76)90040-x · Cited by 5,374
On Optimal Use of a Patchy Environment
MacArthur, R. H., & Pianka, E. R. (1966) · The American Naturalist · doi:10.1086/282454 · Cited by 4,593
A sensorimotor account of vision and visual consciousness
O'Regan, J. K., & Noë, A. (2001) · Behavioral and Brain Sciences · doi:10.1017/s0140525x01000115 · Cited by 3,126 · cited 1×
“This is eloquently expressed in the explorative behaviors of young infants (e.g., grasping and manipulating objects during proprioceptive exploration and then bringing them into visual view during intermodal exploration) (Rochat, 1989; O’Regan and Noë, 2001; Noë, 2004).”
BackgroundThe psychology of curiosity: A review and reinterpretation.
Loewenstein, G. (1994) · Psychological Bulletin · doi:10.1037/0033-2909.116.1.75 · Cited by 2,738 · cited 5×
“In contrast, a consensus has emerged in behavioral psychology that learning represents the primary drive underlying explorative behaviors (Archer and Birke, 1983; Loewenstein, 1994; Silvia, 2005; Pisula, 2009).”
BackgroundInfluentialThe information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 2×
“Epsilon machines introduced by Crutchfield and Young (1989) and the information bottleneck approach introduced by Tishby et al. (1999) combine these first two principles of maximizing predictive information and constraining complexity.”
BackgroundConfirmation, disconfirmation, and information in hypothesis testing
Klayman, J., & Ha, Y.-W. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.211 · Cited by 2,094 · cited 6×
“…difference between the modes of the current and future internal models (Baron, 2005; Nelson, 2005): Predicted L1 change (PLC) predicts the average L1 distance between the current and future internal models (Klayman and Ha, 1987): We tested agents that approximately maximize PMC or PLC using VI.”
BackgroundMethodInfluentialMayr, E. (1961) · Science · doi:10.1126/science.134.3489.1501 · Cited by 1,950
The free-energy principle: a rough guide to the brain?
Friston, K. (2009) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2009.04.005 · Cited by 1,831
Cited by
Curiosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815
“Many approaches measure information gain for exploration (Little & Sommer, 2014; Still & Precup, 2012; Storck et al., 1995).”
BackgroundActive inference and epistemic value
Friston, K., Rigoli, F., Ognibene, D., Mathys, C., Fitzgerald, T., & Pezzulo, G. (2015) · Cognitive Neuroscience · doi:10.1080/17588928.2015.1020053 · Cited by 731
VIME: Variational Information Maximizing Exploration
Houthooft, R., Chen, X., Duan, Y., Schulman, J., Turck, F. D., & Abbeel, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09674 · Cited by 472
An Artificial Sensory Neuron with Tactile Perceptual Learning
Wan, C., Chen, G., Fu, Y., Wang, M., Matsuhisa, N., Pan, S., Pan, L., Yang, H., Wan, Q., Zhu, L., et al. (2018) · Advanced Materials · doi:10.1002/adma.201801291 · Cited by 418
Wan, C., Cai, P., Wang, M., Qian, Y., Huang, W., & Chen, X. (2020) · Advanced Materials · doi:10.1002/adma.201902434 · Cited by 343
Metadata
- Authors
- Little, D. Y., & Sommer, F. T.
- Venue
- Frontiers in Neural Circuits
- Publisher
- Frontiers Media SA
- Published
- 2013
- Volume
- 7
- Pages
- 37-37
- ISSN
- 1662-5110 (ISSN-L)
- OpenAlex
- W2078150668
- Cited by
- 89
- References
- 13
- FWCI
- 7.36
- 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: Learning and exploration in action-perception loops. https://app.cochat.ai/papers/10.3389/fncir.2013.00037
- The paper
- Little, D. Y., & Sommer, F. T. (2013). Learning and exploration in action-perception loops. Frontiers in Neural Circuits. https://doi.org/10.3389/fncir.2013.00037
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.