HOME

TheInfoList



OR:

Action selection is a way of characterizing the most basic problem of intelligent systems: what to do next. In
artificial intelligence Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...
and computational cognitive science, "the action selection problem" is typically associated with
intelligent agents In artificial intelligence, an intelligent agent (IA) is anything which perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or may use knowledge. They may be simple or co ...
and
animat Animat are artificial animals and is a contraction of animal and materials. The term includes physical robots and virtual simulations. The animat model includes features of a simple animal capable of interacting with its environment. It is, therefo ...
s—artificial systems that exhibit complex behaviour in an agent environment. The term is also sometimes used in
ethology Ethology is the scientific study of animal behaviour, usually with a focus on behaviour under natural conditions, and viewing behaviour as an evolutionarily adaptive trait. Behaviourism as a term also describes the scientific and objecti ...
or animal behavior. 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 ''contracting a muscle cell'' to ''provoking a war''. Typically for any one action-selection mechanism, the set of possible actions is predefined and fixed. Most researchers working in this field place high demands on their agents: * The acting agent typically must select its action in
dynamic Dynamics (from Greek δυναμικός ''dynamikos'' "powerful", from δύναμις ''dynamis'' "power") or dynamic may refer to: Physics and engineering * Dynamics (mechanics) ** Aerodynamics, the study of the motion of air ** Analytical dyna ...
and
unpredictable Unpredictable may refer to: Film and TV * "Unpredictable" (''Eureka''), an episode of ''Eureka'' Music Albums * ''Unpredictable'' (Classified album), 2000 * ''Unpredictable'' (Jamie Foxx album), 2005 * ''Unpredictable'' (Malik B. album), 2015 ...
environments. * The agents typically act in real time; therefore they must make decisions in a timely fashion. * 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?) * The environment the agents operate in may include
humans Humans (''Homo sapiens'') are the most abundant and widespread species of primate, characterized by bipedalism and exceptional cognitive skills due to a large and complex brain. This has enabled the development of advanced tools, culture, ...
, who may make things more difficult for the agent (either intentionally or by attempting to assist.) * The agents themselves are often intended to
model A model is an informative representation of an object, person or system. The term originally denoted the plans of a building in late 16th-century English, and derived via French and Italian ultimately from Latin ''modulus'', a measure. Models c ...
animals or humans, and animal/human behaviour is quite complicated. For these reasons action selection is not trivial and attracts a good deal of research.


Characteristics of the action selection problem

The main problem for action selection is complexity. Since all computation 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
bias Bias is a disproportionate weight ''in favor of'' or ''against'' an idea or thing, usually in a way that is closed-minded, prejudicial, or unfair. Biases can be innate or learned. People may develop biases for or against an individual, a group ...
ed, and constrain their search in some way. For AI, the question of action selection is ''what is the best way to constrain this search''? For biology and ethology, the question is ''how do various types of animals constrain their search? Do all animals use the same approaches? Why do they use the ones they do?'' 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 emergent 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 ''some'' mechanism for action selection. This mechanism may be highly distributed (as in the case of distributed organisms such as social insect colonies or
slime mold Slime mold or slime mould is an informal name given to several kinds of unrelated eukaryotic organisms with a life cycle that includes a free-living single-celled stage and the formation of spores. Spores are often produced in macroscopic mul ...
) or it may be a special-purpose module. The action selection mechanism (ASM) determines not only the agent's actions in terms of impact on the world, but also directs its perceptual attention, and updates its
memory Memory is the faculty of the mind by which data or information is encoded, stored, and retrieved when needed. It is the retention of information over time for the purpose of influencing future action. If past events could not be remembered ...
. These
egocentric Egocentrism is the inability to differentiate between self and other. More specifically, it is the inability to accurately assume or understand any perspective other than one's own. Egocentrism is found across the life span: in infancy, early chi ...
sorts of actions may in turn result in modifying the agent's basic behavioural capacities, particularly in that updating memory implies some form of
machine learning Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine ...
is possible. Ideally, action selection itself should also be able to learn and adapt, but there are many problems of combinatorial complexity and computational tractability that may require restricting the search space for learning. In AI, an ASM is also sometimes either referred to as an agent architecture or thought of as a substantial part of one.


AI mechanisms

Generally, artificial action selection mechanisms can be divided into several categories: symbol-based systems sometimes known as classical planning, distributed solutions, and reactive or
dynamic planning is a licensing company owned by manga artist Go Nagai. It was established in 1974 as a sister company of Dynamic Productions. Dynamic Planning is credited in all of Go Nagai's animated works since 1974 as the "planner" and/or "producer". ...
. Some approaches do not fall neatly into any one of these categories. Others are really more about providing
scientific model Scientific modelling is a scientific activity, the aim of which is to make a particular part or feature of the world easier to understand, define, quantify, visualize, or simulate by referencing it to existing and usually commonly accepted ...
s than practical AI control; these last are described further in the next section.


Symbolic approaches

Early in the
history of artificial intelligence The history of artificial intelligence (AI) began in ancient history, antiquity, with myths, stories and rumors of artificial beings endowed with intelligence or consciousness by master craftsmen. The seeds of modern AI were planted by philoso ...
, it was assumed that the best way for an agent to choose what to do next would be to compute a probably optimal plan, and then execute that plan. This led to the physical symbol system hypothesis, that a physical agent that can manipulate symbols is
necessary and sufficient In logic and mathematics, necessity and sufficiency are terms used to describe a conditional or implicational relationship between two statements. For example, in the conditional statement: "If then ", is necessary for , because the truth of ...
for intelligence. Many software agents 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
predicate logic First-order logic—also known as predicate logic, quantificational logic, and first-order predicate calculus—is a collection of formal systems used in mathematics, philosophy, linguistics, and computer science. First-order logic uses quantifie ...
. 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.
Satisficing Satisficing is a decision-making strategy or cognitive heuristic that entails searching through the available alternatives until an acceptability threshold is met. The term ''satisficing'', a portmanteau of ''satisfy'' and ''suffice'', was introduc ...
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 the outcome calculus. Goal driven architectures – In these symbolic 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 the process slightly recursive. Technically, more or less, the plans exploits condition-rules. These architectures are
reactive Reactive may refer to: *Generally, capable of having a reaction (disambiguation) *An adjective abbreviation denoting a bowling ball coverstock made of reactive resin *Reactivity (chemistry) *Reactive mind *Reactive programming See also *Reactanc ...
or hybrid. Classical examples of goal driven architectures are implementable refinements of belief-desire-intention architecture lik
JAM
o
IVE


Distributed approaches

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 modules 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 artificial neural networks research. In practice, there is almost always ''some'' centralised system determining which module is "the most active" or has the most salience. There is evidence real biological brains also have such executive decision systems which evaluate which of the competing systems deserves the most attention, or more properly, has its desired actions disinhibited. * is an attention-based architecture developed by Mary-Anne Williams, 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. * Various types of winner-take-all architectures, in which the single selected action takes full control of the motor system * Spreading activation including Maes Nets (ANA) * Extended Rosenblatt & Payton is a spreading activation architecture developed by Toby Tyrrell in 1993. The agent's behaviour is stored in the form of a hierarchical
connectionism Connectionism refers to both an approach in the field of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN) and to a wide range of techniques and algorithms using ANNs in the context of artificial in ...
network, which Tyrrell named free-flow hierarchy. Recently exploited for example b
de Sevin & Thalmann
(2005) o
Kadleček
(2001). * Behavior based AI, 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
subsumption architecture Subsumption architecture is a reactive robotic architecture heavily associated with behavior-based robotics which was very popular in the 1980s and 90s. The term was introduced by Rodney Brooks and colleagues in 1986.Brooks, R. A., "A Robust Progr ...
, these consisted of different layers which could monitor and suppress each other's inputs and outputs. * Creatures are virtual pets from a computer game driven by three-layered neural network, 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 o
Grand et al.
(1997) and i
The Creatures Developer Resources
See also th
Creatures Wiki


Dynamic planning approaches

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. Dynamic or
reactive planning In artificial intelligence, reactive planning denotes a group of techniques for action selection by autonomous agents. These techniques differ from classical planning in two aspects. First, they operate in a timely fashion and hence can cope wi ...
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
combinatorial explosion In mathematics, a combinatorial explosion is the rapid growth of the complexity of a problem due to how the combinatorics of the problem is affected by the input, constraints, and bounds of the problem. Combinatorial explosion is sometimes used to ...
. On the other hand, they are sometimes seen as too rigid to be considered strong AI, 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. Example dynamic planning mechanisms include: *
Finite-state machines A finite-state machine (FSM) or finite-state automaton (FSA, plural: ''automata''), finite automaton, or simply a state machine, is a mathematical model of computation. It is an abstract machine that can be in exactly one of a finite number o ...
These are
reactive Reactive may refer to: *Generally, capable of having a reaction (disambiguation) *An adjective abbreviation denoting a bowling ball coverstock made of reactive resin *Reactivity (chemistry) *Reactive mind *Reactive programming See also *Reactanc ...
architectures used mostly for computer game agents, in particular for first-person shooters bots, or for virtual movie actors. Typically, the state-machines are hierarchical. For concrete game examples, se
Halo 2 bots paper
by Damian Isla (2005) o

by Jan Paul van Waveren (2001). For a movie example, see Softimage. * Other structured reactive plans tend to look a little more like conventional plans, often with ways to represent hierarchical and
sequential In mathematics, a sequence is an enumerated collection of objects in which repetitions are allowed and order matters. Like a set, it contains members (also called ''elements'', or ''terms''). The number of elements (possibly infinite) is called th ...
structure. Some, such as PRS's 'acts', have support for partial plans. Many agent architectures from the mid-1990s included such plans as a "middle layer" that provided organization for low-level behavior modules while being directed by a higher level real-time planner. Despite this supposed
interoperability Interoperability is a characteristic of a product or system to work with other products or systems. While the term was initially defined for information technology or systems engineering services to allow for information exchange, a broader defi ...
with automated planners, most structured reactive plans are hand coded (Bryson 2001, ch. 3). Examples of structured reactive plans include James Firby'
RAP
System and the Nils Nilsson'
Teleo-reactive plans
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 (o

action selection system, which is a part of Joanna Bryson's Behaviour Oriented Design. 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 of any such system is that when the agent needs to select an action, some solution exists that can be used immediately (see further anytime algorithm).


Others


CogniTAO
is a decision making engine it based on BDI (belief-desire-intention), it includes built in teamwork capabilities. * Soar is a symbolic
cognitive architecture A cognitive architecture refers to both a theory about the structure of the human mind and to a computational instantiation of such a theory used in the fields of artificial intelligence (AI) and computational cognitive science. The formalized mod ...
. It is based on condition-action rules known as productions. Programmers can use the Soar development toolkit for building both reactive and planning agents, or any compromise between these two extremes. * '
Excalibur
'' was a research project led by Alexander Nareyek featuring any-time planning agents for computer games. The architecture is based on structural
constraint satisfaction In artificial intelligence and operations research, constraint satisfaction is the process of finding a solution through a set of constraints that impose conditions that the variables must satisfy. A solution is therefore a set of values for th ...
, which is an advanced
artificial intelligence Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...
technique. *
ACT-R ACT-R (pronounced /ˌækt ˈɑr/; short for "Adaptive Control of Thought—Rational") is a cognitive architecture mainly developed by John Robert Anderson and Christian Lebiere at Carnegie Mellon University. Like any cognitive architecture, ACT-R ...
is similar to Soar. It includes a
Bayesian Thomas Bayes (/beɪz/; c. 1701 – 1761) was an English statistician, philosopher, and Presbyterian minister. Bayesian () refers either to a range of concepts and approaches that relate to statistical methods based on Bayes' theorem, or a followe ...
learning system to help prioritize the productions. * ABL/Hap * Fuzzy architectures The Fuzzy approach 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
reactive Reactive may refer to: *Generally, capable of having a reaction (disambiguation) *An adjective abbreviation denoting a bowling ball coverstock made of reactive resin *Reactivity (chemistry) *Reactive mind *Reactive programming See also *Reactanc ...
and symbolic.


Theories of action selection in nature

Many dynamic models of artificial action selection were originally inspired by research in
ethology Ethology is the scientific study of animal behaviour, usually with a focus on behaviour under natural conditions, and viewing behaviour as an evolutionarily adaptive trait. Behaviourism as a term also describes the scientific and objecti ...
. In particular,
Konrad Lorenz Konrad Zacharias Lorenz (; 7 November 1903 – 27 February 1989) was an Austrian zoologist, ethologist, and ornithologist. He shared the 1973 Nobel Prize in Physiology or Medicine with Nikolaas Tinbergen and Karl von Frisch. He is often regarde ...
and
Nikolaas Tinbergen Nikolaas "Niko" Tinbergen (; ; 15 April 1907 – 21 December 1988) was a Dutch biologist and ornithologist who shared the 1973 Nobel Prize in Physiology or Medicine with Karl von Frisch and Konrad Lorenz for their discoveries concerning the o ...
provided the idea of an
innate releasing mechanism A fixed action pattern is an ethological term describing an instinctive behavioral sequence that is highly stereotyped and species-characteristic. Fixed action patterns are said to be produced by the innate releasing mechanism, a "hard-wired" neura ...
to explain instinctive behaviors (
fixed action pattern A fixed action pattern is an ethological term describing an instinctive behavioral sequence that is highly stereotyped and species-characteristic. Fixed action patterns are said to be produced by the innate releasing mechanism, a "hard-wired" neura ...
s). Influenced by the ideas of William McDougall, Lorenz developed this into a " psychohydraulic" model of the motivation of behavior. In ethology, these ideas were influential in the 1960s, but they are now regarded as outdated because of their use of an energy flow metaphor; the
nervous system In biology, the nervous system is the highly complex part of an animal that coordinates its actions and sensory information by transmitting signals to and from different parts of its body. The nervous system detects environmental changes ...
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.
Stan Franklin Stan Franklin (born August 14, 1931) is an American scientist. He is the W. Harry Feinstone Interdisciplinary Research Professor at the University of Memphis in Memphis, Tennessee, and co-director of the Institute of Intelligent Systems.Shepar ...
has proposed that action selection is the right perspective to take in understanding the role and evolution of mind. See his page o
the action selection paradigm


AI models of neural action selection

Some researchers create elaborate models of neural action selection. See for example: * Th
Computational Cognitive Neuroscience Lab
(CU Boulder). * Th
Adaptive Behaviour Research Group
(Sheffield).


Catecholaminergic Neuron Electron Transport (CNET)

The locus coeruleus (LC) is one of the primary sources of
noradrenaline Norepinephrine (NE), also called noradrenaline (NA) or noradrenalin, is an organic chemical in the catecholamine family that functions in the brain and body as both a hormone and neurotransmitter. The name "noradrenaline" (from Latin '' ad'', ...
in the brain, and has been associated with selection of cognitive processing, such as attention and behavioral tasks. The substantia nigra pars compacta (SNc) is one of the primary sources of dopamine in the brain, and has been associated with action selection, primarily as part of the
basal ganglia The basal ganglia (BG), or basal nuclei, are a group of subcortical nuclei, of varied origin, in the brains of vertebrates. In humans, and some primates, there are some differences, mainly in the division of the globus pallidus into an exter ...
.  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
action potential An action potential occurs when the membrane potential of a specific cell location rapidly rises and falls. This depolarization then causes adjacent locations to similarly depolarize. Action potentials occur in several types of animal cells, ...
. 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: 1)
Ferritin Ferritin is a universal intracellular protein that stores iron and releases it in a controlled fashion. The protein is produced by almost all living organisms, including archaea, bacteria, algae, higher plants, and animals. It is the primary ' ...
and
neuromelanin Neuromelanin (NM) is a dark pigment found in the brain which is structurally related to melanin. It is a polymer of 5,6-dihydroxyindole monomers. Neuromelanin is found in large quantities in catecholaminergic cells of the substantia nigra pars com ...
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 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 tunneling and to route/switch the path of the neurons was subsequently obtained. 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 membrane potential 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 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. 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 generate high energy triplet state electrons by Prof. Doug Brash at Yale, which could provide a source for electrons for the CNET mechanism. 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 optical probes to determine whether electron tunneling associated with ferritin in the neurons is occurring in association with specific actions.  


See also

* Action description language *
Artificial intelligence in video games In video games, artificial intelligence (AI) is used to generate responsive, adaptive or intelligent behaviors primarily in non-player characters (NPCs) similar to human-like intelligence. Artificial intelligence has been an integral part of vid ...
* Cognitive robotics * Expert system * Inference engine *
Intelligent agent In artificial intelligence, an intelligent agent (IA) is anything which perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or may use knowledge. They may be simple or ...
* OPS5 * Production system *
Reinforcement learning Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...
*
Rete algorithm The Rete algorithm ( , , rarely , ) is a pattern matching algorithm for implementing rule-based systems. The algorithm was developed to efficiently apply many rules or patterns to many objects, or facts, in a knowledge base. It is used to dete ...
* Utility system


References


Further reading

* Bratman, M.: Intention, plans, and practical reason. Cambridge, Mass: Harvard University Press (1987) * Brom, C., Lukavský, J., Šerý, O., Poch, T., Šafrata, P.
Affordances and level-of-detail AI for virtual humans
In: Proceedings of Game Set and Match 2, Delft (2006) * Bryson, J.
Intelligence by Design: Principles of Modularity and Coordination for Engineering Complex Adaptive Agents
PhD thesis
Massachusetts Institute of Technology
(2001) * Champandard, A. J.
AI Game Development: Synthetic Creatures with learning and Reactive Behaviors
New Riders, USA (2003) * Grand, S., Cliff, D., Malhotra, A.
Creatures: Artificial life autonomous software-agents for home entertainment
In: Johnson, W. L. (eds.): Proceedings of the First International Conference on Autonomous Agents. ACM press (1997) 22-29 * Huber, M. J.

In: Proceedings of the Third International Conference on Autonomous Agents (Agents'99). Seattle (1999) 236-243 * Isla, D.

In: Gamastura online, 03/11 (2005) * Maes, P.
The agent network architecture (ANA)
In: SIGART Bulletin, 2 (4), pages 115–120 (1991) * Nareyek, A

* Reynolds, C. W
Flocks, Herds, and Schools: A Distributed Behavioral Model
In: Computer Graphics, 21(4) (SIGGRAPH '87 Conference Proceedings) (1987) 25-34. * de Sevin, E. Thalmann, D
A motivational Model of Action Selection for Virtual Humans
In: Computer Graphics International (CGI), IEEE Computer SocietyPress, New York (2005) * Tyrrell, T.
Computational Mechanisms for Action Selection
Ph.D. Dissertation. Centre for Cognitive Science, University of Edinburgh (1993) * van Waveren, J. M. P.: The Quake III Arena Bot. Master thesis. Faculty ITS, University of Technology Delft (2001) * Wooldridge, M
An Introduction to MultiAgent Systems
John Wiley & Sons (2002)


External links

* The University of Memphis

* Michael Wooldridge
Introduction to agents and their action selection mechanisms
* Cyril Brom

* ttps://web.archive.org/web/20060507174634/http://sitemaker.umich.edu/soar Soar project University of Michigan.
Modelling natural action selection
a special issue published by
The Royal Society The Royal Society, formally The Royal Society of London for Improving Natural Knowledge, is a learned society and the United Kingdom's national academy of sciences. The society fulfils a number of roles: promoting science and its benefits, r ...
-
Philosophical Transactions of the Royal Society ''Philosophical Transactions of the Royal Society'' is a scientific journal published by the Royal Society. In its earliest days, it was a private venture of the Royal Society's secretary. It was established in 1665, making it the first journa ...
{{Differentiable computing Artificial intelligence Motor control Motor cognition