English
Related papers

Related papers: What makes math problems hard for reinforcement le…

200 papers

Rule-based reinforcement learning has been gaining popularity ever since DeepSeek-R1 has demonstrated its success through simple verifiable rewards. In the domain of document analysis, reinforcement learning is not as prevalent, even though…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Michael Jungo , Andreas Fischer

We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory. We introduce a mathematical model based on the online learning…

Machine Learning · Computer Science 2022-01-13 Robi Bhattacharjee , Gaurav Mahajan

Using theory and experiments, this paper shows that the difficulty of making tradeoffs offers a parsimonious explanation for a wide range of behavioral phenomena. We develop a model of imprecise comparisons applicable to multiattribute,…

General Economics · Economics 2026-04-01 Cassidy Shubatt , Jeffrey Yang

In this work we present deep learning implementations of two popular theoretical constrained optimization algorithms in infinite dimensional Hilbert spaces, namely, the penalty and the augmented Lagrangian methods. We test these algorithms…

Optimization and Control · Mathematics 2024-01-09 Pinak Mandal

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

The replicability crisis in the social, behavioral, and data sciences has led to the formulation of algorithm frameworks for replicability -- i.e., a requirement that an algorithm produce identical outputs (with high probability) when run…

Machine Learning · Computer Science 2023-11-01 Eric Eaton , Marcel Hussing , Michael Kearns , Jessica Sorrell

Judgment aggregation is a framework to aggregate individual opinions on multiple, logically connected issues into a collective outcome. These opinions are cast by judges, which can be for example referees, experts, advisors or jurors,…

Computer Science and Game Theory · Computer Science 2024-04-01 Robert Bredereck , Junjie Luo

We consider the optimal sample complexity theory of tabular reinforcement learning (RL) for maximizing the infinite horizon discounted reward in a Markov decision process (MDP). Optimal worst-case complexity results have been developed for…

Machine Learning · Computer Science 2023-10-03 Shengbo Wang , Jose Blanchet , Peter Glynn

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their…

Machine Learning · Computer Science 2023-12-19 Sandesh Kamath , Sankalp Mittal , Amit Deshpande , Vineeth N Balasubramanian

In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple…

Machine Learning · Computer Science 2025-02-18 Eric Eaton , Marcel Hussing , Michael Kearns , Aaron Roth , Sikata Bela Sengupta , Jessica Sorrell

Despite recent advancements in machine learning, in practice, relevant datasets are often distributed among market competitors who are reluctant to share. To incentivize data sharing, recent works propose analytics markets, where multiple…

General Economics · Economics 2025-08-05 Thomas Falconer , Jalal Kazempour , Pierre Pinson

We study incremental knapsack problems with profits given by a special class of monotone submodular functions, that we dub all-or-nothing. We show that these problems are not harder to approximate than a less general class of modular…

Data Structures and Algorithms · Computer Science 2023-04-26 Federico D'Onofrio , Yuri Faenza , Lingyi Zhang

Supervised learning in a binary perceptron is able to classify an extensive number of random patterns by a proper assignment of binary synaptic weights. However, to find such assignments in practice, is quite a nontrivial task. The relation…

Disordered Systems and Neural Networks · Physics 2014-11-19 Haiping Huang , Yoshiyuki Kabashima

In many combinatorial problems one may need to model the diversity or similarity of assignments in a solution. For example, one may wish to maximise or minimise the number of distinct values in a solution. To formulate problems of this…

Artificial Intelligence · Computer Science 2014-01-17 Emmanuel Hebrard , Dániel Marx , Barry O'Sullivan , Igor Razgon

Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We…

Machine Learning · Computer Science 2021-02-26 Vincent Zhuang , Yanan Sui

We propose an automata-theoretic approach for reinforcement learning (RL) under complex spatio-temporal constraints with time windows. The problem is formulated using a Markov decision process under a bounded temporal logic constraint.…

Artificial Intelligence · Computer Science 2023-08-01 Xiaoshan Lin , Abbasali Koochakzadeh , Yasin Yazicioglu , Derya Aksaray

While machine learning can myopically reinforce social inequalities, it may also be used to dynamically seek equitable outcomes. In this paper, we formalize long-term fairness in the context of online reinforcement learning. This…

Machine Learning · Computer Science 2024-10-02 Tongxin Yin , Reilly Raab , Mingyan Liu , Yang Liu

We show a close connection between structural hardness for $k$-partite graphs and tight inapproximability results for scheduling problems with precedence constraints. Assuming a natural but nontrivial generalisation of the bipartite…

Computational Complexity · Computer Science 2015-07-08 Abbas Bazzi , Ashkan Norouzi-Fard

Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without consideration of fairness, AI agents can introduce disparities…

Machine Learning · Computer Science 2025-01-03 Sahand Rezaei-Shoshtari , Hanna Yurchyk , Scott Fujimoto , Doina Precup , David Meger

For substructural logics with contraction or weakening admitting cut-free sequent calculi, proof search was analyzed using well-quasi-orders on $\mathbb{N}^d$ (Dickson's lemma), yielding Ackermannian upper bounds via controlled bad-sequence…

Logic in Computer Science · Computer Science 2026-02-24 A. R. Balasubramanian , Vitor Greati , Revantha Ramanayake