frame problem
In plain wordsThe difficulty of getting an AI to work out what does and does not change when something happens, without spelling out every one of the countless things that stay the same.
- 1
Logic-based AI
The difficulty, when actions are described in formal logic, of capturing what an action does not affect: unless every unchanged fact is restated in so-called frame axioms, the system cannot conclude that it still holds. In John McCarthy and Patrick Hayes's situation calculus, painting a block changes its color but not its position or anything else in the world, yet a logical system cannot assume this unless told. Solutions developed from the 1970s to the 1990s include default reasoningnon-monotonic reasoning, n.: Reasoning in which new information can overturn earlier conclusions — you assume a bird can fly until you learn it is a penguin — as people do constantly but classical logic does not allow. and circumscription, STRIPS-style representations in which unmentioned facts persist, and Raymond Reiter's successor-state axioms. Related difficulties are the qualification problem (listing every precondition of an action) and the ramification problem (capturing indirect effects).
- 2
Philosophy and cognitive science
The broader problem of relevance: how a reasoner, natural or artificial, in an open-ended world manages to update just the beliefs an event bears on and to set everything else aside, without first checking all it knows. Daniel Dennett, Jerry Fodor and Hubert Dreyfus treated it as a deep obstacle to symbolic AIsymbolic AI, n.: An approach to AI that writes knowledge down as human-readable symbols and rules, such as 'every bird has wings', and reasons by manipulating them step by step instead of learning patterns from data.. Whether learned systems such as large language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. solve it, by absorbing statistical knowledge of relevance from data, or merely sidestep it, remains debated.
Dennett's robot, busily deducing that moving the wagon won't change the color of the walls while the bomb ticks, is the frame problem in miniature.
Origin
Introduced by John McCarthy and Patrick J. Hayes in 'Some Philosophical Problems from the Standpoint of Artificial Intelligence' (Machine Intelligence 4, 1969). Daniel Dennett's 'Cognitive Wheels: The Frame Problem of AI' (1984), with its bomb-defusing robots, popularized the broader philosophical reading.
Usage note
AI researchers have objected that philosophers stretched the term well beyond its technical meaning, so the two senses should be kept distinct. Unrelated to Marvin Minsky's framesframe, n.: In classic AI, a ready-made template for a familiar kind of thing or event, such as a kitchen or a job interview, with blanks to fill in and sensible default values., a knowledge-representation scheme.
Related
- commonsense reasoningcommonsense reasoning, n.: The everyday background knowledge and reasoning people take for granted — dropped glasses break, hungry people eat, nobody is in two places at once — which machines long struggled to match.
- non-monotonic reasoningnon-monotonic reasoning, n.: Reasoning in which new information can overturn earlier conclusions — you assume a bird can fly until you learn it is a penguin — as people do constantly but classical logic does not allow.
- symbolic AIsymbolic AI, n.: An approach to AI that writes knowledge down as human-readable symbols and rules, such as 'every bird has wings', and reasons by manipulating them step by step instead of learning patterns from data.
- good old-fashioned AIgood old-fashioned AI, n.: A nickname for the classic style of AI, dominant from the 1950s to the 1980s, that tried to make computers intelligent by writing knowledge and rules down by hand.
- Dreyfus's critique of AIDreyfus's critique of AI, n.: The philosopher Hubert Dreyfus's argument, from the 1960s on, that rule-based AI could never match human intelligence, because much human skill rests on bodily know-how and intuition rather than explicit rules.
- Polanyi's paradoxPolanyi's paradox, n.: The observation that we know how to do many things — recognize a face, ride a bike — that we cannot explain in words. That made such skills hard to program until machines learned them from examples.
Sources
- McCarthy, J. & Hayes, P. J. (1969). Some Philosophical Problems from the Standpoint of Artificial Intelligence. In B. Meltzer & D. Michie (eds.), Machine Intelligence 4. Edinburgh University Press.
- Dennett, D. C. (1984). Cognitive Wheels: The Frame Problem of AI. In C. Hookway (ed.), Minds, Machines and Evolution. Cambridge University Press.
Mentioned in
commonsense reasoningcommonsense reasoning, n.: The everyday background knowledge and reasoning people take for granted — dropped glasses break, hungry people eat, nobody is in two places at once — which machines long struggled to match., Daniel DennettDaniel Dennett, prop. n.: An American philosopher who argued that minds are what brains do, that consciousness can in principle be explained scientifically, and that we understand machines by treating them as if they had beliefs and goals., frameframe, n.: In classic AI, a ready-made template for a familiar kind of thing or event, such as a kitchen or a job interview, with blanks to fill in and sensible default values., Hubert DreyfusHubert Dreyfus, prop. n.: An American philosopher who argued from the 1960s that computers following explicit rules could never match human intelligence, which rests on bodily, intuitive know-how., John McCarthyJohn McCarthy, prop. n.: The American computer scientist who coined the term 'artificial intelligence', invented the Lisp programming language and championed formal logic as the route to machine common sense., Dreyfus's critique of AIDreyfus's critique of AI, n.: The philosopher Hubert Dreyfus's argument, from the 1960s on, that rule-based AI could never match human intelligence, because much human skill rests on bodily know-how and intuition rather than explicit rules., Jerry FodorJerry Fodor, prop. n.: An American philosopher who argued that thinking is computation in an inner 'language of thought', and that neural networks cannot explain the structured nature of thought., non-monotonic reasoningnon-monotonic reasoning, n.: Reasoning in which new information can overturn earlier conclusions — you assume a bird can fly until you learn it is a penguin — as people do constantly but classical logic does not allow., situation calculussituation calculus, n.: A logical language for describing how the world changes as actions happen, so that a program can work out what will be true after any sequence of actions., STRIPSSTRIPS, prop. n.: An early AI planning program, and the simple action language it introduced, in which each action lists what must be true beforehand, what becomes true and what stops being true.