A real-world rational agent: unifying old and new AI
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Abstract Explanations of cognitive processes provided by traditional artificial intelligence were based on the notion of the knowledge level. This perspective has been challenged by new AI that proposes an approach based on embodied systems that interact with the real‐world. We demonstrate that these two views can be unified. Our argument is based on the assumption that knowledge level explanations can be defined in the context of Bayesian theory while the goals of new AI are captured by using a well established robot based model of learning and problem solving, called Distributed Adaptive Control (DAC). In our analysis we consider random foraging and we prove that minor modifications of the DAC architecture renders a model that is equivalent to a Bayesian analysis of this task. Subsequently, we compare this enhanced, “rational,” model to its “non‐rational” predecessor and a further control condition using both simulated and real robots, in a variety of environments. Our results show that the changes made to the DAC architecture, in order to unify the perspectives of old and new AI, also lead to a significant improvement in random foraging.
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
The Framing of Decisions and the Psychology of Choice
Tversky, A., & Kahneman, D. (1981) · Science · doi:10.1126/science.7455683 · Cited by 18,497
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
Searle, J. R. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00005756 · Cited by 6,954
Rao, R. P. N., & Ballard, D. H. (1999) · Nature Neuroscience · doi:10.1038/4580 · Cited by 5,483 · cited 2×
“This learning rule is related to filtering theory and state estimation (Kalman, 1960), and similar approaches have been applied to modeling the cortical mechanisms of perceptual learning (Rao, 1999; Rao & Ballard, 1999 ).”
MethodIntelligence without representation
Brooks, R. A. (1991) · Artificial Intelligence · doi:10.1016/0004-3702(91)90053-m · Cited by 4,853
Harnad, S. (1990) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(90)90087-6 · Cited by 4,235 · cited 1×
“This view has been criticized on several grounds and a number of fundamental problems have been identified; the frame problem (McCarthy & Hayes, 1969), the symbol grounding problem ( Harnad, 1990; Searle, 1982), the frame of reference problem (Clancey, 1989a), and the problem of situatedness (Suchman, 1987) (see Pfeif…”
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
Newell, A. (1982) · Artificial Intelligence · doi:10.1016/0004-3702(82)90012-1 · Cited by 2,589 · cited 2×
“On one hand the knowledge level can be seen as expressing an observer stance towards an intelligent system where knowledge and goals are attributed to an artificial system (Chandrasekaran, 1994; Clancey, 1996; Newell, 1982).”
BackgroundNeural correlates of decision variables in parietal cortex
Platt, M. L., & Glimcher, P. W. (1999) · Nature · doi:10.1038/22268 · Cited by 1,721 · cited 2×
“For instance, it has been shown that neurons in the parietal cortex of monkeys accurately represent key decision making variables such as expected gain and gain magnitude (Platt & Glimcher, 1999).”
BackgroundNeuronal Coding of Prediction Errors
Schultz, W., & Dickinson, A. (2000) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.23.1.473 · Cited by 1,427 · cited 2×
“Biological systems do explicitly represent the quality of behavioral states ( Schultz & Dickinson, 2000 ), however, they are not assigned on a fixed a priori basis to specific events but again subject to learning ( Hollerman & Schultz, 1998).”
Background
Cited by
The neural systems that mediate human perceptual decision making
Heekeren, H. R., Marrett, S., & Ungerleider, L. G. (2008) · Nature Reviews Neuroscience · doi:10.1038/nrn2374 · Cited by 875
40 years of cognitive architectures: core cognitive abilities and practical applications
Kotseruba, I., & Tsotsos, J. K. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-018-9646-y · Cited by 539
The Newell Test for a theory of cognition
Anderson, J. R., & Lebiere, C. (2003) · Behavioral and Brain Sciences · doi:10.1017/s0140525x0300013x · Cited by 291
The why, what, where, when and how of goal-directed choice: neuronal and computational principles
Verschure, P. F. M. J., Pennartz, C. M. A., & Pezzulo, G. (2014) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2013.0483 · Cited by 131
Artificial cognition vs. artificial intelligence for next-generation autonomous robotic agents
Sandini, G., Sciutti, A., & Morasso, P. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2024.1349408 · Cited by 40
Metadata
- Authors
- Verschure, P.
- Venue
- Cognitive Science
- Publisher
- Wiley
- Published
- 2003-08
- Volume
- 27
- Issue
- 4
- Pages
- 561-590
- ISSN
- 0364-0213 (ISSN-L)
- OpenAlex
- W2145371424
- Cited by
- 112
- References
- 13
- FWCI
- 2.43
- Type
- journal article
- Language
- en
- Open access
- bronze
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: A real-world rational agent: unifying old and new AI. https://app.cochat.ai/papers/10.1016/s0364-0213(03)00034-x
- The paper
- Verschure, P. (2003). A real-world rational agent: unifying old and new AI. Cognitive Science. https://doi.org/10.1016/s0364-0213(03)00034-x
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.