3391:
3371:
270:
architectures, the agent's behaviour is typically described by a set of goals. Each goal can be achieved by a process or an activity, which is described by a prescripted plan. The agent must just decide which process to carry on to accomplish a given goal. The plan can expand to subgoals, which makes
745:
of those neurons sufficiently to cause the electrons to be routed to the neuron or neurons with the most post-synaptic activity for the purpose of action selection. At the time, prevailing explanations of the purpose of those neurons was that they did not mediate action selection and were only
753:
While evidence of a number of physical predictions of the CNET hypothesis has thus been obtained, evidence of whether the hypothesis itself is correct has not been sought. One way to try to determine whether the CNET mechanism is present in these neurons would be to use quantum dot fluorophores and
504:
Sometimes to attempt to address the perceived inflexibility of dynamic planning, hybrid techniques are used. In these, a more conventional AI planning system searches for new plans when the agent has spare time, and updates the dynamic plan library when it finds good solutions. The important aspect
259:
is a decision-making strategy that attempts to meet criteria for adequacy, rather than identify an optimal solution. A satisficing strategy may often, in fact, be (near) optimal if the costs of the decision-making process itself, such as the cost of obtaining complete information, are considered in
749:
3) Several sources of electrons or excitons to provide the energy for the mechanism were hypothesized in 2018 but had not been observed at that time. Dioxetane cleavage (which can occur during somatic dopamine metabolism by quinone degradation of melanin) was contemporaneously proposed to
734:
observed. Those structures would also need to provide a routing or switching function, which had also not previously been proposed or observed. Evidence of the presence of ferritin and neuromelanin structures in those neurons and their ability to both conduct electrons by sequential
636:
and the control of behavior are now normally treated as involving information transmission rather than energy flow. Dynamic plans and neural networks are more similar to information transmission, while spreading activation is more similar to the diffuse control of emotional / hormonal systems.
733:
are present in high concentrations in those neurons, but it was unknown in 2018 whether they formed structures that would be capable of transmitting electrons over relatively long distances on the scale of microns between the largest of those neurons, which had not been previously proposed or
2369:
746:
modulatory and non-specific. Prof. Pascal Kaeser of
Harvard Medical School subsequently obtained evidence that large SNc neurons can be temporally and spatially specific and mediate action selection. Other evidence indicates that the large LC axons have similar behavior.
718:. CNET is a hypothesized neural signaling mechanism in the SNc and LC (which are catecholaminergic neurons), that could assist with action selection by routing energy between neurons in each group as part of action selection, to help one or more neurons in each group to reach
962:
Poe, Gina R.; Foote, Stephen; Eschenko, Oxana; Johansen, Joshua P.; Bouret, Sebastien; Aston-Jones, Gary; Harley, Carolyn W.; Manahan-Vaughan, Denise; Weinshenker, David; Valentino, Rita; Berridge, Craig; Chandler, Daniel J.; Waterhouse, Barry; Sara, Susan J. (2020-09-17).
334:, Benjamin Johnston and their PhD student Rony Novianto. It orchestrates a diversity of modular distributed processes that can use their own representations and techniques to perceive the environment, process information, plan actions and propose actions to perform.
300:
running in parallel and determining the best action based on local expertise. In these idealized systems, overall coherence is expected to emerge somehow, possibly through careful design of the interacting components. This approach is often inspired by
2234:
Pisano, Filippo; Pisanello, Marco; Lee, Suk Joon; Lee, Jaeeon; Maglie, Emanuela; Balena, Antonio; Sileo, Leonardo; Spagnolo, Barbara; Bianco, Marco; Hyun, Minsuk; De
Vittorio, Massimo; Sabatini, Bernardo L.; Pisanello, Ferruccio (November 2019).
253:. Critics of this approach complain that it is too slow for real-time planning and that, despite the proofs, it is still unlikely to produce optimal plans because reducing descriptions of reality to logic is a process prone to errors.
416:
Dynamic or reactive planning methods compute just one next action in every instant based on the current context and pre-scripted plans. In contrast to classical planning methods, reactive or dynamic approaches do not suffer
295:
In contrast to the symbolic approach, distributed systems of action selection actually have no one "box" in the agent which decides the next action. At least in their idealized form, distributed systems have many
2111:
Sulzer, David; Cassidy, Clifford; Horga, Guillermo; Kang, Un Jung; Fahn, Stanley; Casella, Luigi; Pezzoli, Gianni; Langley, Jason; Hu, Xiaoping P.; Zucca, Fabio A.; Isaias, Ioannis U.; Zecca, Luigi (2018-04-10).
376:, was a response to the slow speed of robots using symbolic action selection techniques. In this form, separate modules respond to different stimuli and generate their own responses. In the original form, the
2410:
89:
The agents are normally created to perform several different tasks. These tasks may conflict for resource allocation (e.g. can the agent put out a fire and deliver a cup of coffee at the same time?)
56:
One problem for understanding action selection is determining the level of abstraction used for specifying an "act". At the most basic level of abstraction, an atomic act could be anything from
3265:
1559:
Tribl, Florian; Asan, Esther; Arzberger, Thomas; Tatschner, Thomas; Langenfeld, Elmar; Meyer, Helmut E.; Bringmann, Gerhard; Riederer, Peter; Gerlach, Manfred; Marcus, Katrin (August 2009).
392:, which is adaptive. Their mechanism is reactive since the network at every time step determines the task that has to be performed by the pet. The network is described well in the paper of
583:
in action selection produces more smooth behaviour than can be produced by architectures exploiting boolean condition-action rules (like Soar or POSH). These architectures are mostly
496:. PRS, RAPs & TRP are no longer developed or supported. One still-active (as of 2006) descendant of this approach is the Parallel-rooted Ordered Slip-stack Hierarchical (or
860:
3107:
413:
Because purely distributed systems are difficult to construct, many researchers have turned to using explicit hard-coded plans to determine the priorities of their system.
2513:
741:
2) ) The axons of large SNc neurons were known to have extensive arbors, but it was unknown whether post-synaptic activity at the synapses of those axons would raise the
249:
still use this approach for action selection. It normally requires describing all sensor readings, the world, all of ones actions and all of one's goals in some form of
1446:"Ferritin and neuromelanin "quantum dot" array structures in dopamine neurons of the substantia nigra pars compacta and norepinephrine neurons of the locus coeruleus"
522:
2486:
1938:
Behl, Tapan; Kaur, Ishnoor; Sehgal, Aayush; Singh, Sukhbir; Makeen, Hafiz A.; Albratty, Mohammed; Alhazmi, Hassan A.; Bhatia, Saurabh; Bungau, Simona (July 2022).
1747:
Friedrich, I.; Reimann, K.; Jankuhn, S.; Kirilina, E.; Stieler, J.; Sonntag, M.; Meijer, J.; Weiskopf, N.; Reinert, T.; Arendt, T.; Morawski, M. (2021-03-22).
425:, since the plans are coded in advance. At the same time, natural intelligence can be rigid in some contexts although it is fluid and able to adapt in others.
3425:
145:
property of an intelligent agent's behavior. However, if we consider how we are going to build an intelligent agent, then it becomes apparent there must be
2169:
Premi, S.; Wallisch, S.; Mano, C. M.; Weiner, A. B.; Bacchiocchi, A.; Wakamatsu, K.; Bechara, E. J. H.; Halaban, R.; Douki, T.; Brash, D. E. (2015-02-19).
127:
takes both time and space (in memory), agents cannot possibly consider every option available to them at every instant in time. Consequently, they must be
722:. It was first proposed in 2018, and is based on a number of physical parameters of those neurons, which can be broken down into three major components:
172:
sorts of actions may in turn result in modifying the agent's basic behavioural capacities, particularly in that updating memory implies some form of
309:
centralised system determining which module is "the most active" or has the most salience. There is evidence real biological brains also have such
2623:
2351:
754:
optical probes to determine whether electron tunneling associated with ferritin in the neurons is occurring in association with specific actions.
141:
One fundamental question about action selection is whether it is really a problem at all for an agent, or whether it is just a description of an
2451:
542:. Programmers can use the Soar development toolkit for building both reactive and planning agents, or any compromise between these two extremes.
2506:
769:
550:
was a research project led by
Alexander Nareyek featuring any-time planning agents for computer games. The architecture is based on structural
160:
The action selection mechanism (ASM) determines not only the agent's actions in terms of impact on the world, but also directs its perceptual
2387:
1415:
750:
generate high energy triplet state electrons by Prof. Doug Brash at Yale, which could provide a source for electrons for the CNET mechanism.
1096:
Feng, Jiesi; Zhang, Changmei; Lischinsky, Julieta; Jing, Miao; Zhou, Jingheng; Wang, Huan; Zhang, Yajun; Dong, Ao; Wu, Zhaofa (2018-10-23).
3296:
811:
539:
480:
with automated planners, most structured reactive plans are hand coded (Bryson 2001, ch. 3). Examples of structured reactive plans include
442:
3397:
2948:
2685:
384:
356:
is a spreading activation architecture developed by Toby
Tyrrell in 1993. The agent's behaviour is stored in the form of a hierarchical
338:
1628:"Indication of quantum mechanical electron transport in human substantia nigra tissue from conductive atomic force microscopy analysis"
365:
628:
of behavior. In ethology, these ideas were influential in the 1960s, but they are now regarded as outdated because of their use of an
230:
3209:
2836:
2643:
2499:
1530:
505:
of any such system is that when the agent needs to select an action, some solution exists that can be used immediately (see further
224:
200:
856:
3164:
1148:"Noradrenaline and Dopamine Neurons in the Reward/Effort Trade-Off: A Direct Electrophysiological Comparison in Behaving Monkeys"
656:
617:
137:
how do various types of animals constrain their search? Do all animals use the same approaches? Why do they use the ones they do?
3445:
472:. Many agent architectures from the mid-1990s included such plans as a "middle layer" that provided organization for low-level
422:
284:
3351:
3291:
2889:
1272:"Neurons gating behavior—developmental, molecular and functional features of neurons in the Substantia Nigra pars reticulata"
882:
2372:. In: Johnson, W. L. (eds.): Proceedings of the First International Conference on Autonomous Agents. ACM press (1997) 22-29
2884:
2573:
2461:
2434:
528:
149:
mechanism for action selection. This mechanism may be highly distributed (as in the case of distributed organisms such as
3430:
3326:
2680:
2633:
2628:
2478:
271:
the process slightly recursive. Technically, more or less, the plans exploits condition-rules. These architectures are
3377:
2673:
2599:
763:
1997:"Locus Coeruleus Norepinephrine in Learned Behavior: Anatomical Modularity and Spatiotemporal Integration in Targets"
176:
is possible. Ideally, action selection itself should also be able to learn and adapt, but there are many problems of
1749:"Cell specific quantitative iron mapping on brain slices by immuno-µPIXE in healthy elderly and Parkinson's disease"
3001:
2936:
2537:
2114:"Neuromelanin detection by magnetic resonance imaging (MRI) and its promise as a biomarker for Parkinson's disease"
609:
302:
3402:
3260:
2899:
2730:
2553:
2430:
van
Waveren, J. M. P.: The Quake III Arena Bot. Master thesis. Faculty ITS, University of Technology Delft (2001)
489:
389:
2379:. In: Proceedings of the Third International Conference on Autonomous Agents (Agents'99). Seattle (1999) 236-243
3440:
3301:
2558:
675:
441:, or for virtual movie actors. Typically, the state-machines are hierarchical. For concrete game examples, see
437:
These are reactive architectures used mostly for computer game agents, in particular for first-person shooters
377:
2362:
1940:"The Locus Coeruleus – Noradrenaline system: Looking into Alzheimer's therapeutics with rose coloured glasses"
211:. Some approaches do not fall neatly into any one of these categories. Others are really more about providing
2472:
3346:
3331:
2984:
2979:
2879:
2747:
2528:
1329:
Stephenson-Jones, Marcus; Samuelsson, Ebba; Ericsson, Jesper; Robertson, Brita; Grillner, Sten (July 2011).
555:
551:
418:
30:
3435:
3306:
3066:
2785:
2780:
820:
535:
446:
238:
2352:
Intelligence by Design: Principles of
Modularity and Coordination for Engineering Complex Adaptive Agents
64:. Typically for any one action-selection mechanism, the set of possible actions is predefined and fixed.
3336:
3321:
3286:
2974:
2874:
2742:
2424:
1720:
1119:
629:
3204:
2344:
380:, these consisted of different layers which could monitor and suppress each other's inputs and outputs.
1331:"Evolutionary Conservation of the Basal Ganglia as a Common Vertebrate Mechanism for Action Selection"
393:
3356:
3311:
2757:
2702:
2548:
2543:
2448:
2340:
Bratman, M.: Intention, plans, and practical reason. Cambridge, Mass: Harvard
University Press (1987)
2182:
1639:
1457:
1342:
1033:
621:
613:
575:
433:
348:
297:
96:, who may make things more difficult for the agent (either intentionally or by attempting to assist.)
2931:
2909:
2658:
2653:
2611:
2563:
204:
83:
3370:
2383:
361:
3316:
2894:
2723:
2319:
2272:
1977:
1863:
1796:
1702:
1691:"Indication of Highly Correlated Electron Transport in Disordered Multilayer Ferritin Structures"
1671:
1608:
1536:
1491:
1376:
1195:
1069:
944:
775:
742:
735:
605:
565:
481:
331:
276:
188:
38:
233:, it was assumed that the best way for an agent to choose what to do next would be to compute a
3382:
3174:
2826:
2697:
2690:
2482:
2311:
2264:
2256:
2216:
2198:
2151:
2133:
2093:
2075:
2036:
2018:
1969:
1961:
1920:
1902:
1855:
1837:
1788:
1770:
1663:
1655:
1600:
1582:
1526:
1483:
1475:
1421:
1411:
1368:
1360:
1311:
1293:
1252:
1234:
1187:
1169:
1061:
1002:
984:
936:
928:
887:
796:
584:
506:
473:
438:
372:
272:
208:
181:
76:
72:
46:
34:
29:
is a way of characterizing the most basic problem of intelligent systems: what to do next. In
2292:"Amine-Functionalized Graphene Quantum Dots for Fluorescence-Based Immunosensing of Ferritin"
3117:
2924:
2718:
2668:
2663:
2606:
2594:
2303:
2248:
2206:
2190:
2141:
2125:
2083:
2067:
2026:
2008:
1951:
1910:
1894:
1845:
1827:
1778:
1760:
1694:
1647:
1590:
1572:
1518:
1465:
1403:
1350:
1301:
1283:
1242:
1226:
1177:
1159:
1105:
1051:
1043:
992:
976:
920:
790:
719:
477:
310:
275:
or hybrid. Classical examples of goal driven architectures are implementable refinements of
234:
212:
173:
2467:
596:
Many dynamic models of artificial action selection were originally inspired by research in
3240:
3184:
3006:
2648:
2568:
2455:
2391:
1733:
1132:
864:
695:
660:
250:
246:
199:
Generally, artificial action selection mechanisms can be divided into several categories:
2417:
2404:
2171:"Chemiexcitation of melanin derivatives induces DNA photoproducts long after UV exposure"
546:
341:
architectures, in which the single selected action takes full control of the motor system
2420:. In: Computer Graphics International (CGI), IEEE Computer SocietyPress, New York (2005)
2186:
1643:
1461:
1346:
500:) action selection system, which is a part of Joanna Bryson's Behaviour Oriented Design.
111:
For these reasons action selection is not trivial and attracts a good deal of research.
3214:
3179:
3169:
2994:
2752:
2578:
2211:
2146:
2088:
2031:
1996:
1915:
1850:
1815:
1783:
1748:
1595:
1560:
1306:
1271:
1247:
1182:
1147:
1056:
997:
832:
826:
814: – computer program typically used to provide some form of artificial intelligence
699:
633:
100:
20:
1627:
714:
in the brain, and has been associated with action selection, primarily as part of the
670:
Some researchers create elaborate models of neural action selection. See for example:
652:
493:
131:, and constrain their search in some way. For AI, the question of action selection is
3419:
3159:
3139:
3056:
2735:
2323:
2276:
1981:
1800:
1706:
1651:
1561:"Identification of L-ferritin in Neuromelanin Granules of the Human Substantia Nigra"
1540:
1470:
1445:
1073:
948:
784:
715:
707:
640:
601:
357:
177:
150:
1675:
1612:
1495:
1214:
360:
network, which
Tyrrell named free-flow hierarchy. Recently exploited for example by
3245:
3076:
2236:
1867:
1380:
1230:
1199:
1164:
730:
469:
461:
318:
2427:. Ph.D. Dissertation. Centre for Cognitive Science, University of Edinburgh (1993)
2413:. In: Computer Graphics, 21(4) (SIGGRAPH '87 Conference Proceedings) (1987) 25–34.
2055:
2071:
1956:
1939:
1395:
1047:
460:
tend to look a little more like conventional plans, often with ways to represent
215:
than practical AI control; these last are described further in the next section.
3341:
3112:
3021:
3016:
2638:
2616:
2376:
2054:
Brash, Douglas E.; Goncalves, Leticia C.P.; Bechara, Etelvino J.H. (June 2018).
1995:
Breton-Provencher, Vincent; Drummond, Gabrielle T.; Sur, Mriganka (2021-06-07).
1882:
1510:
1407:
908:
580:
476:
while being directed by a higher level real-time planner. Despite this supposed
280:
256:
124:
2290:
Garg, Mayank; Vishwakarma, Neelam; Sharma, Amit L.; Singh, Suman (2021-07-08).
2113:
1898:
1765:
1577:
1522:
1021:
964:
924:
787: – Computer system emulating the decision-making ability of a human expert
3235:
3194:
3189:
3102:
3011:
2919:
2831:
2811:
2252:
2129:
2013:
1832:
1355:
1330:
1288:
1038:
980:
625:
497:
465:
242:
169:
154:
120:
2363:
AI Game
Development: Synthetic Creatures with learning and Reactive Behaviors
2315:
2260:
2237:"Depth-resolved fiber photometry with a single tapered optical fiber implant"
2202:
2170:
2137:
2079:
2022:
1965:
1906:
1841:
1774:
1659:
1586:
1479:
1364:
1297:
1238:
1173:
988:
932:
485:
3230:
3199:
3097:
2941:
2904:
2841:
2795:
2790:
2775:
2397:
2370:
Creatures: Artificial life autonomous software-agents for home entertainment
2291:
2194:
1698:
703:
647:
is the right perspective to take in understanding the role and evolution of
450:
314:
161:
142:
104:
2491:
2307:
2268:
2220:
2155:
2097:
2040:
1973:
1924:
1859:
1792:
1690:
1667:
1604:
1487:
1425:
1372:
1315:
1256:
1191:
1065:
1006:
940:
421:. On the other hand, they are sometimes seen as too rigid to be considered
67:
Most researchers working in this field place high demands on their agents:
1517:, Advances in Quantum Chemistry, vol. 82, Elsevier, pp. 25–111,
3132:
2964:
1689:
Rourk, Christopher; Huang, Yunbo; Chen, Minjing; Shen, Cai (2021-06-16).
726:
711:
597:
50:
2355:
3255:
3092:
3046:
2969:
2869:
2864:
2816:
1215:"Mechanisms of Action Selection and Timing in Substantia Nigra Neurons"
738:
and to route/switch the path of the neurons was subsequently obtained.
1394:
Guatteo, Ezia; Cucchiaroni, Maria
Letizia; Mercuri, Nicola B. (2009),
1146:
Varazzani, C.; San-Galli, A.; Gilardeau, S.; Bouret, S. (2015-05-20).
778: – robot with processing architecture that will allow it to learn
525:(belief-desire-intention), it includes built in teamwork capabilities.
3270:
3250:
3122:
2914:
1400:
Birth, Life and Death of Dopaminergic Neurons in the Substantia Nigra
532:
397:
267:
165:
93:
42:
682:
1110:
1097:
3071:
3051:
3041:
3036:
3031:
3026:
2989:
2821:
561:
241:
hypothesis, that a physical agent that can manipulate symbols is
3061:
1098:"A genetically encoded fluorescent sensor for rapid and specific
802:
648:
313:
which evaluate which of the competing systems deserves the most
128:
2495:
1881:
Liu, Changliang; Goel, Pragya; Kaeser, Pascal S. (2021-04-09).
877:
772: – AI used for video games, usually non-player characters
388:
are virtual pets from a computer game driven by three-layered
37:, "the action selection problem" is typically associated with
859:." Biologically Inspired Cognitive Architectures (2010): 98.
2462:
Introduction to agents and their action selection mechanisms
401:
184:
that may require restricting the search space for learning.
2468:
Slides on a course on action selection of artificial beings
2418:
A motivational Model of Action Selection for Virtual Humans
2411:
Flocks, Herds, and Schools: A Distributed Behavioral Model
2343:
Brom, C., LukavskĂ˝, J., Ĺ erĂ˝, O., Poch, T., Ĺ afrata, P.:
1402:, no. 73, Vienna: Springer Vienna, pp. 91–101,
805: – rule-based or production system computer language
449:
by Jan Paul van Waveren (2001). For a movie example, see
187:
In AI, an ASM is also sometimes either referred to as an
86:; therefore they must make decisions in a timely fashion.
45:—artificial systems that exhibit complex behaviour in an
702:
in the brain, and has been associated with selection of
468:
structure. Some, such as PRS's 'acts', have support for
2347:. In: Proceedings of Game Set and Match 2, Delft (2006)
518:
1883:"Spatial and temporal scales of dopamine transmission"
2345:
Affordances and level-of-detail AI for virtual humans
1022:"The locus coeruleus mediates behavioral flexibility"
909:"Locus Coeruleus in time with the making of memories"
837:
Pages displaying wikidata descriptions as a fallback
816:
Pages displaying wikidata descriptions as a fallback
807:
Pages displaying wikidata descriptions as a fallback
793: – Component of artificial intelligence systems
780:
Pages displaying wikidata descriptions as a fallback
3279:
3223:
3152:
3085:
2957:
2857:
2850:
2804:
2768:
2711:
2587:
2527:
568:
learning system to help prioritize the productions.
2400:. In: SIGART Bulletin, 2 (4), pages 115–120 (1991)
2056:"Chemiexcitation and Its Implications for Disease"
1396:"Substantia Nigra Control of Basal Ganglia Nuclei"
690:Catecholaminergic Neuron Electron Transport (CNET)
237:plan, and then execute that plan. This led to the
92:The environment the agents operate in may include
538:. It is based on condition-action rules known as
1213:Fan, D.; Rossi, M. A.; Yin, H. H. (2012-04-18).
1020:McBurney-Lin, Jim; Yang, Hongdian (2022-09-04).
330:is an attention-based architecture developed by
2487:Philosophical Transactions of the Royal Society
115:Characteristics of the action selection problem
2377:JAM: A BDI-theoretic mobile agent architecture
965:"Locus coeruleus: a new look at the blue spot"
799: – Software agent which acts autonomously
706:, such as attention and behavioral tasks. The
305:research. In practice, there is almost always
2507:
2425:Computational Mechanisms for Action Selection
428:Example dynamic planning mechanisms include:
133:what is the best way to constrain this search
8:
857:Attention in the ASMO cognitive architecture
317:, or more properly, has its desired actions
191:or thought of as a substantial part of one.
135:? For biology and ethology, the question is
99:The agents themselves are often intended to
2854:
2514:
2500:
2492:
1444:Rourk, Christopher John (September 2018).
1270:Partanen, Juha; Achim, Kaia (2022-09-06).
2210:
2145:
2087:
2030:
2012:
1955:
1914:
1849:
1831:
1782:
1764:
1594:
1576:
1469:
1354:
1305:
1287:
1246:
1181:
1163:
1109:
1055:
1037:
996:
835: – modeling approach for video games
157:) or it may be a special-purpose module.
119:The main problem for action selection is
676:Computational Cognitive Neuroscience Lab
521:is a decision making engine it based on
447:the Master's Thesis about Quake III bots
1816:"Reward functions of the basal ganglia"
878:"PRS-CL: A Procedural Reasoning System"
848:
710:(SNc) is one of the primary sources of
203:sometimes known as classical planning,
1729:
1718:
1511:"Functional neural electron transport"
1128:
1117:
770:Artificial intelligence in video games
698:(LC) is one of the primary sources of
592:Theories of action selection in nature
21:Game mechanics § Action selection
2435:An Introduction to MultiAgent Systems
2386:. In: Gamastura online, 03/11 (2005)
2356:Massachusetts Institute of Technology
49:. The term is also sometimes used in
7:
3352:Generative adversarial network (GAN)
2398:The agent network architecture (ANA)
2368:Grand, S., Cliff, D., Malhotra, A.:
1753:Acta Neuropathologica Communications
1091:
1089:
666:AI models of neural action selection
103:animals or humans, and animal/human
75:typically must select its action in
3426:Problems in artificial intelligence
1565:Molecular & Cellular Proteomics
2479:Modelling natural action selection
1626:Rourk, Christopher J. (May 2019).
829: – Pattern matching algorithm
766: – Robot programming language
612:to explain instinctive behaviors (
564:is similar to Soar. It includes a
231:history of artificial intelligence
14:
1944:Biomedicine & Pharmacotherapy
823: – Field of machine learning
683:Adaptive Behaviour Research Group
398:The Creatures Developer Resources
225:Automated planning and scheduling
3390:
3389:
3369:
1652:10.1016/j.biosystems.2019.02.003
1471:10.1016/j.biosystems.2018.07.008
620:, Lorenz developed this into a "
354:Extended Rosenblatt & Payton
2481:, a special issue published by
1814:Schultz, Wolfram (2016-02-02).
913:Current Opinion in Neurobiology
907:Sara, Susan J (December 2015).
79:and unpredictable environments.
3302:Recurrent neural network (RNN)
3292:Differentiable neural computer
2437:. John Wiley & Sons (2002)
1820:Journal of Neural Transmission
1509:Rourk, Christopher J. (2020),
1231:10.1523/jneurosci.5924-11.2012
1165:10.1523/jneurosci.0454-15.2015
883:Artificial Intelligence Center
708:substantia nigra pars compacta
616:). Influenced by the ideas of
1:
3347:Variational autoencoder (VAE)
3307:Long short-term memory (LSTM)
2574:Computational learning theory
2384:Handling complexity in Halo 2
653:the action selection paradigm
3327:Convolutional neural network
2072:10.1016/j.molmed.2018.04.004
2060:Trends in Molecular Medicine
2001:Frontiers in Neural Circuits
1957:10.1016/j.biopha.2022.113179
1102:detection of norepinephrine"
1048:10.1016/j.celrep.2022.111534
82:The agents typically act in
3322:Multilayer perceptron (MLP)
2447:The University of Memphis:
1887:Nature Reviews Neuroscience
1408:10.1007/978-3-211-92660-4_7
969:Nature Reviews Neuroscience
764:Action description language
409:Dynamic planning approaches
3462:
3398:Artificial neural networks
3312:Gated recurrent unit (GRU)
2538:Differentiable programming
2449:Agents by action selection
2416:de Sevin, E. Thalmann, D.:
2296:ACS Applied Nano Materials
1899:10.1038/s41583-021-00455-7
1766:10.1186/s40478-021-01145-2
1578:10.1074/mcp.m900006-mcp200
1523:10.1016/bs.aiq.2020.08.001
1515:Quantum Boundaries of Life
925:10.1016/j.conb.2015.07.004
610:innate releasing mechanism
311:executive decision systems
303:artificial neural networks
222:
18:
3365:
2731:Artificial neural network
2554:Automatic differentiation
2475:. University of Michigan.
2253:10.1038/s41592-019-0581-x
2130:10.1038/s41531-018-0047-3
2014:10.3389/fncir.2021.638007
1833:10.1007/s00702-016-1510-0
1356:10.1016/j.cub.2011.05.001
1289:10.3389/fnins.2022.976209
1276:Frontiers in Neuroscience
1039:10.1101/2022.09.01.506286
981:10.1038/s41583-020-0360-9
458:structured reactive plans
445:by Damian Isla (2005) or
264:Goal driven architectures
58:contracting a muscle cell
2559:Neuromorphic engineering
2522:Differentiable computing
2365:. New Riders, USA (2003)
608:provided the idea of an
378:subsumption architecture
243:necessary and sufficient
178:combinatorial complexity
19:Not to be confused with
3332:Residual neural network
2748:Artificial Intelligence
2195:10.1126/science.1256022
2118:npj Parkinson's Disease
1219:Journal of Neuroscience
1152:Journal of Neuroscience
556:artificial intelligence
554:, which is an advanced
552:constraint satisfaction
419:combinatorial explosion
362:de Sevin & Thalmann
277:belief-desire-intention
245:for intelligence. Many
31:artificial intelligence
3446:Management cybernetics
2308:10.1021/acsanm.1c01398
1728:Cite journal requires
1127:Cite journal requires
821:Reinforcement learning
536:cognitive architecture
291:Distributed approaches
260:the outcome calculus.
239:physical symbol system
3287:Neural Turing machine
2875:Human image synthesis
1699:10.31219/osf.io/7gqmt
614:fixed action patterns
434:Finite-state machines
205:distributed solutions
107:is quite complicated.
3378:Computer programming
3357:Graph neural network
2932:Text-to-video models
2910:Text-to-image models
2758:Large language model
2743:Scientific computing
2549:Statistical manifold
2544:Information geometry
2460:Michael Wooldridge:
2361:Champandard, A. J.:
855:Samsonovich, A. V. "
704:cognitive processing
494:Teleo-reactive plans
345:Spreading activation
201:symbol-based systems
53:or animal behavior.
3431:Functional analysis
2724:In-context learning
2564:Pattern recognition
2187:2015Sci...347..842P
1644:2019BiSys.179...30R
1462:2018BiSys.171...48R
1347:2011CBio...21.1081S
576:Fuzzy architectures
219:Symbolic approaches
3317:Echo state network
3205:JĂĽrgen Schmidhuber
2900:Facial recognition
2895:Speech recognition
2805:Software libraries
2454:2006-04-18 at the
2390:2006-01-08 at the
863:2022-11-06 at the
776:Cognitive robotics
743:membrane potential
659:2006-10-09 at the
651:. See his page on
643:has proposed that
606:Nikolaas Tinbergen
332:Mary-Anne Williams
279:architecture like
207:, and reactive or
189:agent architecture
180:and computational
164:, and updates its
39:intelligent agents
33:and computational
3413:
3412:
3175:Stephen Grossberg
3148:
3147:
2483:The Royal Society
2405:Excalibur project
2247:(11): 1185–1192.
2181:(6224): 842–847.
1417:978-3-211-92659-8
1341:(13): 1081–1091.
1225:(16): 5534–5548.
1158:(20): 7866–7877.
888:SRI International
812:Production system
797:Intelligent agent
618:William McDougall
600:. In particular,
507:anytime algorithm
443:Halo 2 bots paper
373:Behavior based AI
337:Various types of
213:scientific models
47:agent environment
35:cognitive science
16:Computing concept
3453:
3403:Machine learning
3393:
3392:
3373:
3128:Action selection
3118:Self-driving car
2925:Stable Diffusion
2890:Speech synthesis
2855:
2719:Machine learning
2595:Gradient descent
2516:
2509:
2502:
2493:
2409:Reynolds, C. W.
2328:
2327:
2302:(7): 7416–7425.
2287:
2281:
2280:
2231:
2225:
2224:
2214:
2166:
2160:
2159:
2149:
2108:
2102:
2101:
2091:
2051:
2045:
2044:
2034:
2016:
1992:
1986:
1985:
1959:
1935:
1929:
1928:
1918:
1878:
1872:
1871:
1853:
1835:
1811:
1805:
1804:
1786:
1768:
1744:
1738:
1737:
1731:
1726:
1724:
1716:
1714:
1713:
1686:
1680:
1679:
1623:
1617:
1616:
1598:
1580:
1571:(8): 1832–1838.
1556:
1550:
1549:
1548:
1547:
1506:
1500:
1499:
1473:
1441:
1435:
1434:
1433:
1432:
1391:
1385:
1384:
1358:
1326:
1320:
1319:
1309:
1291:
1267:
1261:
1260:
1250:
1210:
1204:
1203:
1185:
1167:
1143:
1137:
1136:
1130:
1125:
1123:
1115:
1113:
1093:
1084:
1083:
1081:
1080:
1059:
1041:
1017:
1011:
1010:
1000:
959:
953:
952:
904:
898:
897:
895:
894:
876:Karen L. Myers.
873:
867:
853:
838:
817:
808:
791:Inference engine
781:
720:action potential
645:action selection
478:interoperability
474:behavior modules
329:
328:
235:probably optimal
209:dynamic planning
174:machine learning
27:Action selection
3461:
3460:
3456:
3455:
3454:
3452:
3451:
3450:
3441:Motor cognition
3416:
3415:
3414:
3409:
3361:
3275:
3241:Google DeepMind
3219:
3185:Geoffrey Hinton
3144:
3081:
3007:Project Debater
2953:
2851:Implementations
2846:
2800:
2764:
2707:
2649:Backpropagation
2583:
2569:Tensor calculus
2523:
2520:
2456:Wayback Machine
2444:
2433:Wooldridge, M.
2392:Wayback Machine
2337:
2335:Further reading
2332:
2331:
2289:
2288:
2284:
2233:
2232:
2228:
2168:
2167:
2163:
2110:
2109:
2105:
2053:
2052:
2048:
1994:
1993:
1989:
1937:
1936:
1932:
1880:
1879:
1875:
1813:
1812:
1808:
1746:
1745:
1741:
1727:
1717:
1711:
1709:
1688:
1687:
1683:
1625:
1624:
1620:
1558:
1557:
1553:
1545:
1543:
1533:
1508:
1507:
1503:
1443:
1442:
1438:
1430:
1428:
1418:
1393:
1392:
1388:
1335:Current Biology
1328:
1327:
1323:
1269:
1268:
1264:
1212:
1211:
1207:
1145:
1144:
1140:
1126:
1116:
1095:
1094:
1087:
1078:
1076:
1019:
1018:
1014:
975:(11): 644–659.
961:
960:
956:
906:
905:
901:
892:
890:
875:
874:
870:
865:Wayback Machine
854:
850:
845:
836:
815:
806:
779:
760:
696:locus coeruleus
692:
668:
661:Wayback Machine
624:" model of the
622:psychohydraulic
594:
515:
488:System and the
411:
400:. See also the
349:Maes Nets (ANA)
339:winner-take-all
326:
325:
293:
251:predicate logic
247:software agents
227:
221:
197:
117:
62:provoking a war
24:
17:
12:
11:
5:
3459:
3457:
3449:
3448:
3443:
3438:
3433:
3428:
3418:
3417:
3411:
3410:
3408:
3407:
3406:
3405:
3400:
3387:
3386:
3385:
3380:
3366:
3363:
3362:
3360:
3359:
3354:
3349:
3344:
3339:
3334:
3329:
3324:
3319:
3314:
3309:
3304:
3299:
3294:
3289:
3283:
3281:
3277:
3276:
3274:
3273:
3268:
3263:
3258:
3253:
3248:
3243:
3238:
3233:
3227:
3225:
3221:
3220:
3218:
3217:
3215:Ilya Sutskever
3212:
3207:
3202:
3197:
3192:
3187:
3182:
3180:Demis Hassabis
3177:
3172:
3170:Ian Goodfellow
3167:
3162:
3156:
3154:
3150:
3149:
3146:
3145:
3143:
3142:
3137:
3136:
3135:
3125:
3120:
3115:
3110:
3105:
3100:
3095:
3089:
3087:
3083:
3082:
3080:
3079:
3074:
3069:
3064:
3059:
3054:
3049:
3044:
3039:
3034:
3029:
3024:
3019:
3014:
3009:
3004:
2999:
2998:
2997:
2987:
2982:
2977:
2972:
2967:
2961:
2959:
2955:
2954:
2952:
2951:
2946:
2945:
2944:
2939:
2929:
2928:
2927:
2922:
2917:
2907:
2902:
2897:
2892:
2887:
2882:
2877:
2872:
2867:
2861:
2859:
2852:
2848:
2847:
2845:
2844:
2839:
2834:
2829:
2824:
2819:
2814:
2808:
2806:
2802:
2801:
2799:
2798:
2793:
2788:
2783:
2778:
2772:
2770:
2766:
2765:
2763:
2762:
2761:
2760:
2753:Language model
2750:
2745:
2740:
2739:
2738:
2728:
2727:
2726:
2715:
2713:
2709:
2708:
2706:
2705:
2703:Autoregression
2700:
2695:
2694:
2693:
2683:
2681:Regularization
2678:
2677:
2676:
2671:
2666:
2656:
2651:
2646:
2644:Loss functions
2641:
2636:
2631:
2626:
2621:
2620:
2619:
2609:
2604:
2603:
2602:
2591:
2589:
2585:
2584:
2582:
2581:
2579:Inductive bias
2576:
2571:
2566:
2561:
2556:
2551:
2546:
2541:
2533:
2531:
2525:
2524:
2521:
2519:
2518:
2511:
2504:
2496:
2490:
2489:
2476:
2470:
2464:
2458:
2443:
2442:External links
2440:
2439:
2438:
2431:
2428:
2421:
2414:
2407:
2401:
2394:
2380:
2375:Huber, M. J.:
2373:
2366:
2359:
2354:. PhD thesis,
2348:
2341:
2336:
2333:
2330:
2329:
2282:
2241:Nature Methods
2226:
2161:
2103:
2066:(6): 527–541.
2046:
1987:
1930:
1893:(6): 345–358.
1873:
1826:(7): 679–693.
1806:
1739:
1730:|journal=
1681:
1618:
1551:
1531:
1501:
1436:
1416:
1386:
1321:
1262:
1205:
1138:
1129:|journal=
1111:10.1101/449546
1085:
1012:
954:
899:
868:
847:
846:
844:
841:
840:
839:
833:Utility system
830:
827:Rete algorithm
824:
818:
809:
800:
794:
788:
782:
773:
767:
759:
756:
691:
688:
687:
686:
679:
667:
664:
634:nervous system
632:metaphor; the
593:
590:
589:
588:
581:fuzzy approach
572:
569:
559:
543:
526:
514:
511:
502:
501:
454:
410:
407:
406:
405:
402:Creatures Wiki
396:(1997) and in
390:neural network
381:
369:
351:
342:
335:
292:
289:
223:Main article:
220:
217:
196:
193:
116:
113:
109:
108:
97:
90:
87:
80:
15:
13:
10:
9:
6:
4:
3:
2:
3458:
3447:
3444:
3442:
3439:
3437:
3436:Motor control
3434:
3432:
3429:
3427:
3424:
3423:
3421:
3404:
3401:
3399:
3396:
3395:
3388:
3384:
3381:
3379:
3376:
3375:
3372:
3368:
3367:
3364:
3358:
3355:
3353:
3350:
3348:
3345:
3343:
3340:
3338:
3335:
3333:
3330:
3328:
3325:
3323:
3320:
3318:
3315:
3313:
3310:
3308:
3305:
3303:
3300:
3298:
3295:
3293:
3290:
3288:
3285:
3284:
3282:
3280:Architectures
3278:
3272:
3269:
3267:
3264:
3262:
3259:
3257:
3254:
3252:
3249:
3247:
3244:
3242:
3239:
3237:
3234:
3232:
3229:
3228:
3226:
3224:Organizations
3222:
3216:
3213:
3211:
3208:
3206:
3203:
3201:
3198:
3196:
3193:
3191:
3188:
3186:
3183:
3181:
3178:
3176:
3173:
3171:
3168:
3166:
3163:
3161:
3160:Yoshua Bengio
3158:
3157:
3155:
3151:
3141:
3140:Robot control
3138:
3134:
3131:
3130:
3129:
3126:
3124:
3121:
3119:
3116:
3114:
3111:
3109:
3106:
3104:
3101:
3099:
3096:
3094:
3091:
3090:
3088:
3084:
3078:
3075:
3073:
3070:
3068:
3065:
3063:
3060:
3058:
3057:Chinchilla AI
3055:
3053:
3050:
3048:
3045:
3043:
3040:
3038:
3035:
3033:
3030:
3028:
3025:
3023:
3020:
3018:
3015:
3013:
3010:
3008:
3005:
3003:
3000:
2996:
2993:
2992:
2991:
2988:
2986:
2983:
2981:
2978:
2976:
2973:
2971:
2968:
2966:
2963:
2962:
2960:
2956:
2950:
2947:
2943:
2940:
2938:
2935:
2934:
2933:
2930:
2926:
2923:
2921:
2918:
2916:
2913:
2912:
2911:
2908:
2906:
2903:
2901:
2898:
2896:
2893:
2891:
2888:
2886:
2883:
2881:
2878:
2876:
2873:
2871:
2868:
2866:
2863:
2862:
2860:
2856:
2853:
2849:
2843:
2840:
2838:
2835:
2833:
2830:
2828:
2825:
2823:
2820:
2818:
2815:
2813:
2810:
2809:
2807:
2803:
2797:
2794:
2792:
2789:
2787:
2784:
2782:
2779:
2777:
2774:
2773:
2771:
2767:
2759:
2756:
2755:
2754:
2751:
2749:
2746:
2744:
2741:
2737:
2736:Deep learning
2734:
2733:
2732:
2729:
2725:
2722:
2721:
2720:
2717:
2716:
2714:
2710:
2704:
2701:
2699:
2696:
2692:
2689:
2688:
2687:
2684:
2682:
2679:
2675:
2672:
2670:
2667:
2665:
2662:
2661:
2660:
2657:
2655:
2652:
2650:
2647:
2645:
2642:
2640:
2637:
2635:
2632:
2630:
2627:
2625:
2624:Hallucination
2622:
2618:
2615:
2614:
2613:
2610:
2608:
2605:
2601:
2598:
2597:
2596:
2593:
2592:
2590:
2586:
2580:
2577:
2575:
2572:
2570:
2567:
2565:
2562:
2560:
2557:
2555:
2552:
2550:
2547:
2545:
2542:
2540:
2539:
2535:
2534:
2532:
2530:
2526:
2517:
2512:
2510:
2505:
2503:
2498:
2497:
2494:
2488:
2484:
2480:
2477:
2474:
2471:
2469:
2465:
2463:
2459:
2457:
2453:
2450:
2446:
2445:
2441:
2436:
2432:
2429:
2426:
2423:Tyrrell, T.:
2422:
2419:
2415:
2412:
2408:
2406:
2402:
2399:
2395:
2393:
2389:
2385:
2381:
2378:
2374:
2371:
2367:
2364:
2360:
2357:
2353:
2349:
2346:
2342:
2339:
2338:
2334:
2325:
2321:
2317:
2313:
2309:
2305:
2301:
2297:
2293:
2286:
2283:
2278:
2274:
2270:
2266:
2262:
2258:
2254:
2250:
2246:
2242:
2238:
2230:
2227:
2222:
2218:
2213:
2208:
2204:
2200:
2196:
2192:
2188:
2184:
2180:
2176:
2172:
2165:
2162:
2157:
2153:
2148:
2143:
2139:
2135:
2131:
2127:
2123:
2119:
2115:
2107:
2104:
2099:
2095:
2090:
2085:
2081:
2077:
2073:
2069:
2065:
2061:
2057:
2050:
2047:
2042:
2038:
2033:
2028:
2024:
2020:
2015:
2010:
2006:
2002:
1998:
1991:
1988:
1983:
1979:
1975:
1971:
1967:
1963:
1958:
1953:
1949:
1945:
1941:
1934:
1931:
1926:
1922:
1917:
1912:
1908:
1904:
1900:
1896:
1892:
1888:
1884:
1877:
1874:
1869:
1865:
1861:
1857:
1852:
1847:
1843:
1839:
1834:
1829:
1825:
1821:
1817:
1810:
1807:
1802:
1798:
1794:
1790:
1785:
1780:
1776:
1772:
1767:
1762:
1758:
1754:
1750:
1743:
1740:
1735:
1722:
1708:
1704:
1700:
1696:
1692:
1685:
1682:
1677:
1673:
1669:
1665:
1661:
1657:
1653:
1649:
1645:
1641:
1637:
1633:
1629:
1622:
1619:
1614:
1610:
1606:
1602:
1597:
1592:
1588:
1584:
1579:
1574:
1570:
1566:
1562:
1555:
1552:
1542:
1538:
1534:
1532:9780128226391
1528:
1524:
1520:
1516:
1512:
1505:
1502:
1497:
1493:
1489:
1485:
1481:
1477:
1472:
1467:
1463:
1459:
1455:
1451:
1447:
1440:
1437:
1427:
1423:
1419:
1413:
1409:
1405:
1401:
1397:
1390:
1387:
1382:
1378:
1374:
1370:
1366:
1362:
1357:
1352:
1348:
1344:
1340:
1336:
1332:
1325:
1322:
1317:
1313:
1308:
1303:
1299:
1295:
1290:
1285:
1281:
1277:
1273:
1266:
1263:
1258:
1254:
1249:
1244:
1240:
1236:
1232:
1228:
1224:
1220:
1216:
1209:
1206:
1201:
1197:
1193:
1189:
1184:
1179:
1175:
1171:
1166:
1161:
1157:
1153:
1149:
1142:
1139:
1134:
1121:
1112:
1107:
1103:
1101:
1092:
1090:
1086:
1075:
1071:
1067:
1063:
1058:
1053:
1049:
1045:
1040:
1035:
1032:(4): 111534.
1031:
1027:
1023:
1016:
1013:
1008:
1004:
999:
994:
990:
986:
982:
978:
974:
970:
966:
958:
955:
950:
946:
942:
938:
934:
930:
926:
922:
918:
914:
910:
903:
900:
889:
885:
884:
879:
872:
869:
866:
862:
858:
852:
849:
842:
834:
831:
828:
825:
822:
819:
813:
810:
804:
801:
798:
795:
792:
789:
786:
785:Expert system
783:
777:
774:
771:
768:
765:
762:
761:
757:
755:
751:
747:
744:
739:
737:
732:
728:
723:
721:
717:
716:basal ganglia
713:
709:
705:
701:
700:noradrenaline
697:
689:
684:
680:
678:(CU Boulder).
677:
673:
672:
671:
665:
663:
662:
658:
654:
650:
646:
642:
641:Stan Franklin
638:
635:
631:
627:
623:
619:
615:
611:
607:
603:
602:Konrad Lorenz
599:
591:
587:and symbolic.
586:
582:
578:
577:
573:
570:
567:
563:
560:
557:
553:
549:
548:
544:
541:
537:
534:
530:
527:
524:
520:
517:
516:
512:
510:
508:
499:
495:
491:
487:
483:
479:
475:
471:
470:partial plans
467:
463:
459:
455:
452:
448:
444:
440:
436:
435:
431:
430:
429:
426:
424:
420:
414:
408:
403:
399:
395:
391:
387:
386:
382:
379:
375:
374:
370:
367:
363:
359:
358:connectionism
355:
352:
350:
346:
343:
340:
336:
333:
324:
323:
322:
320:
316:
312:
308:
304:
299:
290:
288:
286:
282:
278:
274:
269:
265:
261:
258:
254:
252:
248:
244:
240:
236:
232:
229:Early in the
226:
218:
216:
214:
210:
206:
202:
195:AI mechanisms
194:
192:
190:
185:
183:
179:
175:
171:
167:
163:
158:
156:
152:
151:social insect
148:
144:
139:
138:
134:
130:
126:
122:
114:
112:
106:
102:
98:
95:
91:
88:
85:
81:
78:
74:
70:
69:
68:
65:
63:
59:
54:
52:
48:
44:
40:
36:
32:
28:
22:
3246:Hugging Face
3210:David Silver
3127:
2858:Audio–visual
2712:Applications
2691:Augmentation
2536:
2473:Soar project
2466:Cyril Brom:
2403:Nareyek, A.
2350:Bryson, J.:
2299:
2295:
2285:
2244:
2240:
2229:
2178:
2174:
2164:
2121:
2117:
2106:
2063:
2059:
2049:
2004:
2000:
1990:
1947:
1943:
1933:
1890:
1886:
1876:
1823:
1819:
1809:
1756:
1752:
1742:
1721:cite journal
1710:. Retrieved
1684:
1635:
1631:
1621:
1568:
1564:
1554:
1544:, retrieved
1514:
1504:
1453:
1449:
1439:
1429:, retrieved
1399:
1389:
1338:
1334:
1324:
1279:
1275:
1265:
1222:
1218:
1208:
1155:
1151:
1141:
1120:cite journal
1099:
1077:. Retrieved
1029:
1026:Cell Reports
1025:
1015:
972:
968:
957:
916:
912:
902:
891:. Retrieved
881:
871:
851:
752:
748:
740:
731:neuromelanin
724:
693:
685:(Sheffield).
669:
644:
639:
595:
574:
545:
503:
490:Nils Nilsson
462:hierarchical
457:
432:
427:
415:
412:
394:Grand et al.
383:
371:
353:
344:
319:disinhibited
306:
294:
263:
262:
255:
228:
198:
186:
182:tractability
159:
153:colonies or
146:
140:
136:
132:
123:. Since all
118:
110:
66:
61:
57:
55:
26:
25:
3394:Categories
3342:Autoencoder
3297:Transformer
3165:Alex Graves
3113:OpenAI Five
3017:IBM Watsonx
2639:Convolution
2617:Overfitting
630:energy flow
540:productions
482:James Firby
266:– In these
257:Satisficing
125:computation
71:The acting
3420:Categories
3383:Technology
3236:EleutherAI
3195:Fei-Fei Li
3190:Yann LeCun
3103:Q-learning
3086:Decisional
3012:IBM Watson
2920:Midjourney
2812:TensorFlow
2659:Activation
2612:Regression
2607:Clustering
2396:Maes, P.:
2382:Isla, D.:
2007:: 638007.
1950:: 113179.
1712:2022-11-13
1632:Biosystems
1546:2022-11-13
1450:Biosystems
1431:2022-11-13
1282:: 976209.
1079:2022-11-13
893:2013-06-13
843:References
626:motivation
558:technique.
466:sequential
364:(2005) or
347:including
170:egocentric
155:slime mold
121:complexity
3266:MIT CSAIL
3231:Anthropic
3200:Andrew Ng
3098:AlphaZero
2942:VideoPoet
2905:AlphaFold
2842:MindSpore
2796:SpiNNaker
2791:Memristor
2698:Diffusion
2674:Rectifier
2654:Batchnorm
2634:Attention
2629:Adversary
2324:237804893
2316:2574-0970
2277:203848191
2261:1548-7091
2203:0036-8075
2138:2373-8057
2124:(1): 11.
2080:1471-4914
2023:1662-5110
1982:249137521
1966:0753-3322
1907:1471-003X
1842:0300-9564
1801:232322739
1775:2051-5960
1759:(1): 47.
1707:241118606
1660:0303-2647
1638:: 30–38.
1587:1535-9476
1541:229230562
1480:0303-2647
1456:: 48–58.
1365:0960-9822
1298:1662-453X
1239:0270-6474
1174:0270-6474
1074:252187005
989:1471-003X
949:206952441
933:0959-4388
919:: 87–94.
736:tunneling
547:Excalibur
451:Softimage
423:strong AI
385:Creatures
315:attention
162:attention
105:behaviour
84:real time
3374:Portals
3133:Auto-GPT
2965:Word2vec
2769:Hardware
2686:Datasets
2588:Concepts
2452:Archived
2388:Archived
2269:31591577
2221:25700512
2156:29644335
2098:29751974
2041:34163331
1974:35676784
1925:33837376
1860:26838982
1793:33752749
1676:73509918
1668:30826349
1613:23650245
1605:19318681
1496:51722018
1488:30048795
1426:20411770
1373:21700460
1316:36148148
1257:22514315
1192:25995472
1066:36288712
1007:32943779
941:26241632
861:Archived
758:See also
727:Ferritin
712:dopamine
657:Archived
598:ethology
585:reactive
566:Bayesian
533:symbolic
519:CogniTAO
366:KadleÄŤek
273:reactive
268:symbolic
168:. These
143:emergent
51:ethology
3256:Meta AI
3093:AlphaGo
3077:PanGu-ÎŁ
3047:ChatGPT
3022:Granite
2970:Seq2seq
2949:Whisper
2870:WaveNet
2865:AlexNet
2837:Flux.jl
2817:PyTorch
2669:Sigmoid
2664:Softmax
2529:General
2212:4432913
2183:Bibcode
2175:Science
2147:5893576
2089:5975183
2032:8215268
1916:8220193
1868:3894133
1851:5495848
1784:7986300
1640:Bibcode
1596:2722774
1458:Bibcode
1381:9327412
1343:Bibcode
1307:9485944
1248:6703499
1200:6531661
1183:6795183
1100:in vivo
1057:9662304
1034:bioRxiv
998:8991985
571:ABL/Hap
368:(2001).
298:modules
77:dynamic
43:animats
3271:Huawei
3251:OpenAI
3153:People
3123:MuZero
2985:Gemini
2980:Claude
2915:DALL-E
2827:Theano
2358:(2001)
2322:
2314:
2275:
2267:
2259:
2219:
2209:
2201:
2154:
2144:
2136:
2096:
2086:
2078:
2039:
2029:
2021:
1980:
1972:
1964:
1923:
1913:
1905:
1866:
1858:
1848:
1840:
1799:
1791:
1781:
1773:
1705:
1674:
1666:
1658:
1611:
1603:
1593:
1585:
1539:
1529:
1494:
1486:
1478:
1424:
1414:
1379:
1371:
1363:
1314:
1304:
1296:
1255:
1245:
1237:
1198:
1190:
1180:
1172:
1072:
1064:
1054:
1036:
1005:
995:
987:
947:
939:
931:
513:Others
456:Other
166:memory
129:biased
94:humans
3337:Mamba
3108:SARSA
3072:LLaMA
3067:BLOOM
3052:GPT-J
3042:GPT-4
3037:GPT-3
3032:GPT-2
3027:GPT-1
2990:LaMDA
2822:Keras
2320:S2CID
2273:S2CID
1978:S2CID
1864:S2CID
1797:S2CID
1703:S2CID
1672:S2CID
1609:S2CID
1537:S2CID
1492:S2CID
1377:S2CID
1196:S2CID
1070:S2CID
945:S2CID
562:ACT-R
531:is a
101:model
73:agent
3261:Mila
3062:PaLM
2995:Bard
2975:BERT
2958:Text
2937:Sora
2312:ISSN
2265:PMID
2257:ISSN
2217:PMID
2199:ISSN
2152:PMID
2134:ISSN
2094:PMID
2076:ISSN
2037:PMID
2019:ISSN
1970:PMID
1962:ISSN
1921:PMID
1903:ISSN
1856:PMID
1838:ISSN
1789:PMID
1771:ISSN
1734:help
1664:PMID
1656:ISSN
1601:PMID
1583:ISSN
1527:ISBN
1484:PMID
1476:ISSN
1422:PMID
1412:ISBN
1369:PMID
1361:ISSN
1312:PMID
1294:ISSN
1253:PMID
1235:ISSN
1188:PMID
1170:ISSN
1133:help
1062:PMID
1003:PMID
985:ISSN
937:PMID
929:ISSN
803:OPS5
729:and
694:The
681:The
674:The
649:mind
604:and
579:The
529:Soar
498:POSH
464:and
439:bots
327:ASMO
307:some
147:some
41:and
3002:NMT
2885:OCR
2880:HWR
2832:JAX
2786:VPU
2781:TPU
2776:IPU
2600:SGD
2304:doi
2249:doi
2207:PMC
2191:doi
2179:347
2142:PMC
2126:doi
2084:PMC
2068:doi
2027:PMC
2009:doi
1952:doi
1948:151
1911:PMC
1895:doi
1846:PMC
1828:doi
1824:123
1779:PMC
1761:doi
1695:doi
1648:doi
1636:179
1591:PMC
1573:doi
1519:doi
1466:doi
1454:171
1404:doi
1351:doi
1302:PMC
1284:doi
1243:PMC
1227:doi
1178:PMC
1160:doi
1106:doi
1052:PMC
1044:doi
993:PMC
977:doi
921:doi
725:1)
523:BDI
509:).
492:'s
486:RAP
484:'s
285:IVE
283:or
281:JAM
60:to
3422::
2485:-
2318:.
2310:.
2298:.
2294:.
2271:.
2263:.
2255:.
2245:16
2243:.
2239:.
2215:.
2205:.
2197:.
2189:.
2177:.
2173:.
2150:.
2140:.
2132:.
2120:.
2116:.
2092:.
2082:.
2074:.
2064:24
2062:.
2058:.
2035:.
2025:.
2017:.
2005:15
2003:.
1999:.
1976:.
1968:.
1960:.
1946:.
1942:.
1919:.
1909:.
1901:.
1891:22
1889:.
1885:.
1862:.
1854:.
1844:.
1836:.
1822:.
1818:.
1795:.
1787:.
1777:.
1769:.
1755:.
1751:.
1725::
1723:}}
1719:{{
1701:.
1693:.
1670:.
1662:.
1654:.
1646:.
1634:.
1630:.
1607:.
1599:.
1589:.
1581:.
1567:.
1563:.
1535:,
1525:,
1513:,
1490:.
1482:.
1474:.
1464:.
1452:.
1448:.
1420:,
1410:,
1398:,
1375:.
1367:.
1359:.
1349:.
1339:21
1337:.
1333:.
1310:.
1300:.
1292:.
1280:16
1278:.
1274:.
1251:.
1241:.
1233:.
1223:32
1221:.
1217:.
1194:.
1186:.
1176:.
1168:.
1156:35
1154:.
1150:.
1124::
1122:}}
1118:{{
1104:.
1088:^
1068:.
1060:.
1050:.
1042:.
1030:41
1028:.
1024:.
1001:.
991:.
983:.
973:21
971:.
967:.
943:.
935:.
927:.
917:35
915:.
911:.
886:.
880:.
655:.
321:.
287:.
2515:e
2508:t
2501:v
2326:.
2306::
2300:4
2279:.
2251::
2223:.
2193::
2185::
2158:.
2128::
2122:4
2100:.
2070::
2043:.
2011::
1984:.
1954::
1927:.
1897::
1870:.
1830::
1803:.
1763::
1757:9
1736:)
1732:(
1715:.
1697::
1678:.
1650::
1642::
1615:.
1575::
1569:8
1521::
1498:.
1468::
1460::
1406::
1383:.
1353::
1345::
1318:.
1286::
1259:.
1229::
1202:.
1162::
1135:)
1131:(
1114:.
1108::
1082:.
1046::
1009:.
979::
951:.
923::
896:.
453:.
404:.
23:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.