Minimal history, a theory of plausible explanation

Mayfield, John E.

doi:10.1002/cplx.20170

Cited by 7 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Difficulty is just the logarithm of the computational steps that are required to find an acceptable policy, including the execution of several possible policies and verifying them. This is in accordance with Levin's universal search [10,11], the notion of information gain [4] and the interpretation of the "minimal process for creating [something] from nothing" [12].…”

Section: Introductionsupporting

confidence: 84%

“…The relevance of verification in difficulty has usually been associated with deduction. However, some works have incorporated it as well in other inference problems, such as induction and optimisation, using Levin's Kt [4,12,1]. From the setting described in this paper, many other things could be explored, especially around the notions of composition and decomposition, task instance and agent response curves.…”

Section: Difficulty As Levin Search With Stochastic Verificationmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic Tasks: Difficulty and Levin Search

Hernández-Orallo

2015

Artificial General Intelligence

View full text Add to dashboard Cite

Abstract. We establish a setting for asynchronous stochastic tasks that account for episodes, rewards and responses, and, most especially, the computational complexity of the algorithm behind an agent solving a task. This is used to determine the difficulty of a task as the (logarithm of the) number of computational steps required to acquire an acceptable policy for the task, which includes the exploration of policies and their verification. We also analyse instance difficulty, task compositions and decompositions.

show abstract

Section: Introductionsupporting

confidence: 84%

Section: Difficulty As Levin Search With Stochastic Verificationmentioning

confidence: 99%

Stochastic Tasks: Difficulty and Levin Search

Hernández-Orallo

2015

Artificial General Intelligence

View full text Add to dashboard Cite

show abstract

“…Difficulty is just the logarithm of the computational steps that are required to find the optimal policy, including trying several possible policies and verifying them. This is in accordance with Levin's universal search [43,44], the notion of information gain [17] and the interpretation of the "minimal process for creating [something] from nothing" [47]. However, we have to be very careful that when an agent interacts with the world or a task, this task can give hints and reinforce the search process.…”

Section: Introductionsupporting

confidence: 79%

Universal Psychometrics Tasks: difficulty, composition and decomposition

Hernandez-Orallo

2015

Preprint

View full text Add to dashboard Cite

This note revisits the concepts of task and difficulty. The notion of cognitive task and its use for the evaluation of intelligent systems is still replete with issues. The view of tasks as MDP in the context of reinforcement learning has been especially useful for the formalisation of learning tasks. However, this alternate interaction does not accommodate well for some other tasks that are usual in artificial intelligence and, most especially, in animal and human evaluation. In particular, we want to have a more general account of episodes, rewards and responses, and, most especially, the computational complexity of the algorithm behind an agent solving a task. This is crucial for the determination of the difficulty of a task as the (logarithm of the) number of computational steps required to acquire an acceptable policy for the task, which includes the exploration of policies and their verification. We introduce a notion of asynchronous-time stochastic tasks. Based on this interpretation, we can see what task difficulty is, what instance difficulty is (relative to a task) and also what task compositions and decompositions are.

show abstract

“…These include sophistication (Koppel, 1987), computational depth (Antunes et al 2006(Antunes et al , 2009, and minimal history (Mayfield, 2007). The concept of effective complexity developed by Gell-Mann (1995) is closely related to logical density (Ay, Muller, and Szkola, 2010).…”

Section: Complexity Is Logical Densitymentioning

confidence: 99%

Your Digital Afterlives

Steinhart¹

2014

View full text Add to dashboard Cite

Minimal history, a theory of plausible explanation

Abstract: In computational theory, time is defined in terms of Inc. Complexity 12: 48 -53, 2007

Cited by 7 publications

References 10 publications

Stochastic Tasks: Difficulty and Levin Search

Stochastic Tasks: Difficulty and Levin Search

Universal Psychometrics Tasks: difficulty, composition and decomposition

Your Digital Afterlives

Contact Info

Product

Resources

About