English
Related papers

Related papers: Learning programs with magic values

200 papers

The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of…

Machine Learning · Computer Science 2018-05-25 Zhongwen Xu , Hado van Hasselt , David Silver

Deep learning models are widely used for various industrial and scientific applications. Even though these models have achieved considerable success in recent years, there exists a lack of understanding of the rationale behind decisions…

Machine Learning · Computer Science 2020-07-08 Swapnil Nitin Shah

We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification…

Machine Learning · Computer Science 2021-01-21 Abhinav Verma , Hoang M. Le , Yisong Yue , Swarat Chaudhuri

In formal languages and automata theory, the magic number problem can be formulated as follows: for a given integer n, is it possible to find a number d in the range [n,2^n] such that there is no minimal deterministic finite automaton with…

Formal Languages and Automata Theory · Computer Science 2023-09-06 Savinien Kreczman , Luca Prigioniero , Eric Rowland , Manon Stipulanti

Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to make accurate predictions but also to understand the underlying…

Computer Vision and Pattern Recognition · Computer Science 2025-02-17 Utkarsh Mall , Cheng Perng Phoo , Mia Chiquier , Bharath Hariharan , Kavita Bala , Carl Vondrick

The Da Vinci Code, a game of logical deduction and imperfect information, presents unique challenges for artificial intelligence, demanding nuanced reasoning beyond simple pattern recognition. This paper investigates the efficacy of various…

Artificial Intelligence · Computer Science 2025-06-17 LeCheng Zhang , Yuanshi Wang , Haotian Shen , Xujie Wang

Deep probabilistic programming languages try to combine the advantages of deep learning with those of probabilistic programming languages. If successful, this would be a big step forward in machine learning and programming languages.…

Artificial Intelligence · Computer Science 2018-04-19 Guillaume Baudart , Martin Hirzel , Louis Mandel

Motivated by algorithmic information theory, the problem of program discovery can help find candidates of underlying generative mechanisms of natural and artificial phenomena. The uncomputability of such inverse problem, however,…

Information Theory · Computer Science 2021-12-29 Vladimir Lemusa , Eduardo Acuña , Víctor Zamora , Francisco Hernandez-Quiroz , Hector Zenil

We enable aProbLog---a probabilistic logical programming approach---to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms for highly…

Artificial Intelligence · Computer Science 2018-11-16 Federico Cerutti , Lance Kaplan , Angelika Kimmig , Murat Sensoy

Many tasks can be easily solved using machine learning techniques. However, some tasks cannot readily be solved using statistical models, requiring a symbolic approach instead. Program induction is one of the ways that such tasks can be…

Machine Learning · Computer Science 2024-02-13 Ahmad Ayaz Amin

Probabilistic programming has become a standard practice to model stochastic events and learn about the behavior of nature in different scientific contexts, ranging from Genetics and Ecology to Linguistics and Psychology. However, domain…

Programming Languages · Computer Science 2025-07-10 Guilherme Espada , Alcides Fonseca

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…

Machine Learning · Statistics 2023-11-01 David S. Watson , Joshua O'Hara , Niek Tax , Richard Mudd , Ido Guy

Quantum computers promise to solve computational problems significantly faster than classical computers. These 'speed-ups' are achieved by utilizing a resource known as magic. Measuring the amount of magic used by a device allows us to…

Quantum Physics · Physics 2025-11-07 Roy J. Garcia , Gaurav Bhole , Kaifeng Bu , Liyuan Chen , Haribabu Arthanari , Arthur Jaffe

Probabilistic logic programs are logic programs in which some of the facts are annotated with probabilities. Several classical probabilistic inference tasks (such as MAP and computing marginals) have not yet received a lot of attention for…

Artificial Intelligence · Computer Science 2012-02-20 Daan Fierens , Guy Van den Broeck , Ingo Thon , Bernd Gutmann , Luc De Raedt

Solving algebraic word problems requires executing a series of arithmetic operations---a program---to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a…

Artificial Intelligence · Computer Science 2017-10-24 Wang Ling , Dani Yogatama , Chris Dyer , Phil Blunsom

Infinite-state reactive synthesis has attracted significant attention in recent years, which has led to the emergence of novel symbolic techniques for solving infinite-state games. Temporal logics featuring variables over infinite domains…

Logic in Computer Science · Computer Science 2024-11-12 Philippe Heim , Rayna Dimitrova

Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving…

Machine Learning · Computer Science 2023-05-26 Michael Kounavis , Ousmane Dia , Ilqar Ramazanli

Generative AI enables students to produce plausible code quickly. Producing working code is therefore no longer a reliable indicator of understanding. This is particularly problematic in non-computer-science programmes, where time…

Computers and Society · Computer Science 2026-04-09 Christina Maria Mayr

Probabilistic programming languages allow programmers to write down conditional probability distributions that represent statistical and machine learning models as programs that use observe statements. These programs are run by accumulating…

Programming Languages · Computer Science 2021-01-25 Jules Jacobs