Anticipation (artificial intelligence)
Encyclopedia
In artificial intelligence
(AI), anticipation is the concept of an agent
making decisions based on predictions, expectations, or beliefs about the future. It is widely considered that anticipation is a vital component of complex natural cognitive systems. As a branch of AI, anticipatory systems is a specialization still echoing the debates from the 1980s about the necessity for AI for an internal model.
If it rains outside,
take the umbrella.
Otherwise
leave the umbrella home
A system such as the one defined above might be viewed as inherently reactive
because the decision making
is based on the current state of the environment with no explicit regard to the future. An agent employing anticipation would try to predict the future state of the environment (weather in this case) and make use of the predictions in the decision making. For example
If the sky is cloudy and the air pressure is low,
it will probably rain soon
so take the umbrella with you.
Otherwise
leave the umbrella home.
These rules appear more proactive
, because they explicitly take into account possible future events. Notice though that in terms of representation
and reasoning, these two rule sets are identical, both behave in response to existing conditions. Note too that both systems assume the agent is proactively
In practice, systems incorporating reactive planning
tend to be autonomous systems proactively pursuing at least one, and often many, goals. What defines anticipation in an AI model is the explicit existence of an inner model of the environment for the anticipatory system (sometimes including the system itself). For example, if the phrase it will probably rain were computed on line in real time, the system would be seen as anticipatory.
In 1985, Robert Rosen defined an anticipatory system as follows :
In Rosen's work, analysis of the example : "It's raining outside, therefore take the umbrella" does involve a prediction. It involves the prediction that "If it is raining, I will get wet out there unless I have my umbrella". In that sense, even though it is already raining outside, the decision to take an umbrella is not a purely reactive thing. It involves the use of predictive models which tell us what will happen if we don't take the umbrella, when it is already raining outside.
To some extent, Rosen's definition of anticipation applies to any system incorporating machine learning
. At issue is how much of a system's behaviour should or indeed can be determined by reasoning over dedicated representations, how much by on-line planning
, and how much must be provided by the system's designers.
Anticipatory agents belonging to Rosen's definition are easy to see in human mental capabilities of taking decisions at a certain time T taking into account the effects of their own actions at different future timescales T+k. However, Rosen (a theoretical biologist) describes ALL living organisms as examples of naturally occurring anticipatory systems, which means that there must be somatic predictive models (meaning, "of the body"; physical) as components within the organization of all living organisms. No mental process is required for anticipation. In his book, Anticipatory Systems, Rosen describes how even single cellular organisms manifest this behavior pattern. It is logical to hypothesize therefore: If it is true that life is anticipatory in this sense, then the evolution of the conscious mind (such as human beings experience) may be a natural concentration and amplification of the anticipatory nature of life, itself.
Machine learning methods started to integrate anticipatory capabilities in an implicit form as in reinforcement learning
systems (Sutton & Barto, 1998; Balkenius, 1995) where they learn to anticipate future rewards and punishments caused by current actions (Sutton & Barto, 1998). Moreover, anticipation enhanced performance of machine learning techniques to face with complex environments where agents have to guide their attention to collect important information to act (Balkenius & Hulth, 1999).
modifies error back propagation algorithm to change neural network weights in order to decrease the mismatch between anticipated states and states actually experienced in the future (Schmidhuber - Adaptive curiosity and adaptive confidence, 1991). He introduces the concept of curiosity for agents as a measure of the mismatch between expectations and future experienced reality. Agents able to monitor and control their own curiosity explore situations where they expect to engage with novel experiences and are generally able to deal with complex environments more than the others.
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
(AI), anticipation is the concept of an agent
Intelligent agent
In artificial intelligence, an intelligent agent is an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals . Intelligent agents may also learn or use knowledge to achieve their goals...
making decisions based on predictions, expectations, or beliefs about the future. It is widely considered that anticipation is a vital component of complex natural cognitive systems. As a branch of AI, anticipatory systems is a specialization still echoing the debates from the 1980s about the necessity for AI for an internal model.
Reaction, proaction and anticipation
Elementary forms of artificial intelligence can be constructed using a policy based on simple if-then rules. An example of such a system would be an agent following the rulesIf it rains outside,
take the umbrella.
Otherwise
leave the umbrella home
A system such as the one defined above might be viewed as inherently reactive
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 with highly dynamic and unpredictable environments....
because the decision making
Decision making
Decision making can be regarded as the mental processes resulting in the selection of a course of action among several alternative scenarios. Every decision making process produces a final choice. The output can be an action or an opinion of choice.- Overview :Human performance in decision terms...
is based on the current state of the environment with no explicit regard to the future. An agent employing anticipation would try to predict the future state of the environment (weather in this case) and make use of the predictions in the decision making. For example
If the sky is cloudy and the air pressure is low,
it will probably rain soon
so take the umbrella with you.
Otherwise
leave the umbrella home.
These rules appear more proactive
ProActive
ProActive is Java grid middleware for parallel, distributed, and multi-threaded computing. It is developed by the OW2 Consortium, including INRIA, CNRS, University of Nice Sophia Antipolis, and ActiveEon...
, because they explicitly take into account possible future events. Notice though that in terms of representation
Knowledge representation
Knowledge representation is an area of artificial intelligence research aimed at representing knowledge in symbols to facilitate inferencing from those knowledge elements, creating new elements of knowledge...
and reasoning, these two rule sets are identical, both behave in response to existing conditions. Note too that both systems assume the agent is proactively
- leaving the house, and
- trying to stay dry.
In practice, systems incorporating reactive planning
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 with highly dynamic and unpredictable environments....
tend to be autonomous systems proactively pursuing at least one, and often many, goals. What defines anticipation in an AI model is the explicit existence of an inner model of the environment for the anticipatory system (sometimes including the system itself). For example, if the phrase it will probably rain were computed on line in real time, the system would be seen as anticipatory.
In 1985, Robert Rosen defined an anticipatory system as follows :
- A system containing a predictive model of itself and/or its environment,
- which allows it to change state at an instant in accord
- with the model's predictions pertaining to a later instant.
In Rosen's work, analysis of the example : "It's raining outside, therefore take the umbrella" does involve a prediction. It involves the prediction that "If it is raining, I will get wet out there unless I have my umbrella". In that sense, even though it is already raining outside, the decision to take an umbrella is not a purely reactive thing. It involves the use of predictive models which tell us what will happen if we don't take the umbrella, when it is already raining outside.
To some extent, Rosen's definition of anticipation applies to any system incorporating machine learning
Machine learning
Machine learning, a branch of artificial intelligence, is a scientific discipline concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data, such as from sensor data or databases...
. At issue is how much of a system's behaviour should or indeed can be determined by reasoning over dedicated representations, how much by on-line planning
Automated planning and scheduling
Automated planning and scheduling is a branch of artificial intelligence that concerns the realization of strategies or action sequences, typically for execution by intelligent agents, autonomous robots and unmanned vehicles. Unlike classical control and classification problems, the solutions are...
, and how much must be provided by the system's designers.
Anticipation in evolution and cognition
The anticipation of future states is also a major evolutionary and cognitive advance (Sjolander 1995).Anticipatory agents belonging to Rosen's definition are easy to see in human mental capabilities of taking decisions at a certain time T taking into account the effects of their own actions at different future timescales T+k. However, Rosen (a theoretical biologist) describes ALL living organisms as examples of naturally occurring anticipatory systems, which means that there must be somatic predictive models (meaning, "of the body"; physical) as components within the organization of all living organisms. No mental process is required for anticipation. In his book, Anticipatory Systems, Rosen describes how even single cellular organisms manifest this behavior pattern. It is logical to hypothesize therefore: If it is true that life is anticipatory in this sense, then the evolution of the conscious mind (such as human beings experience) may be a natural concentration and amplification of the anticipatory nature of life, itself.
Machine learning methods started to integrate anticipatory capabilities in an implicit form as in reinforcement learning
Reinforcement learning
Inspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
systems (Sutton & Barto, 1998; Balkenius, 1995) where they learn to anticipate future rewards and punishments caused by current actions (Sutton & Barto, 1998). Moreover, anticipation enhanced performance of machine learning techniques to face with complex environments where agents have to guide their attention to collect important information to act (Balkenius & Hulth, 1999).
From Anticipation to Curiosity
Jürgen SchmidhuberJürgen Schmidhuber
Jürgen Schmidhuber is a computer scientist and artist known for his work on machine learning, universal Artificial Intelligence , artificial neural networks, digital physics, and low-complexity art. His contributions also include generalizations of Kolmogorov complexity and the Speed Prior...
modifies error back propagation algorithm to change neural network weights in order to decrease the mismatch between anticipated states and states actually experienced in the future (Schmidhuber - Adaptive curiosity and adaptive confidence, 1991). He introduces the concept of curiosity for agents as a measure of the mismatch between expectations and future experienced reality. Agents able to monitor and control their own curiosity explore situations where they expect to engage with novel experiences and are generally able to deal with complex environments more than the others.
See also
- Action selectionAction selectionAction selection is a way of characterizing the most basic problem of intelligent systems: what to do next. In artificial intelligence and computational cognitive science, "the action selection problem" is typically associated with intelligent agents and animats—artificial systems that exhibit...
- CognitionCognitionIn science, cognition refers to mental processes. These processes include attention, remembering, producing and understanding language, solving problems, and making decisions. Cognition is studied in various disciplines such as psychology, philosophy, linguistics, and computer science...
- Dynamic planningDynamic Planningis 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"....
- The History of artificial intelligenceHistory of artificial intelligenceThe history of artificial intelligence began in antiquity, with myths, stories and rumors of artificial beings endowed with intelligence or consciousness by master craftsmen; as Pamela McCorduck writes, AI began with "an ancient wish to forge the gods."...
- MindRACES
- Nature-nurture
- The Physical symbol systemPhysical symbol systemA physical symbol system takes physical patterns , combining them into structures and manipulating them to produce new expressions....
hypothesis - Strong AIStrong AIStrong AI is artificial intelligence that matches or exceeds human intelligence — the intelligence of a machine that can successfully perform any intellectual task that a human being can. It is a primary goal of artificial intelligence research and an important topic for science fiction writers and...
- Robert Rosen
- TeleonomyTeleonomyTeleonomy is the quality of apparent purposefulness and of goal-directedness of structures and functions in living organisms that derive from their evolutionary history, adaptation for reproductive success, or generally, due to the operation of a program....
External links
- MindRACES: From Reactive to Anticipatory Cognitive Embodied Systems, http://www.mindraces.org, 2004