paper-with-me

홈 › Papers

What makes math problems hard for reinforcement learning: a case study

2024-08-27 · Ali Shehper, Anibal M. Medina-Mardones, Lucas Fagan, Bartłomiej Lewandowski, Angus Gruen, Yang Qiu, Piotr Kucharski, Zhenghan Wang, Sergei Gukov

Using a long-standing conjecture from combinatorial group theory, we explore, from multiple perspectives, the challenges of finding rare instances carrying disproportionately high rewards. Based on lessons learned in the context defined by the Andrews-Curtis conjecture, we propose algorithmic enhancements and a topological hardness measure with implications for a broad class of search problems. As part of our study, we also address several open mathematical questions. Notably, we demonstrate the length reducibility of all but two presentations in the Akbulut-Kirby series (1981), and resolve various potential counterexamples in the Miller-Schupp series (1991), including three infinite subfamilies.

📄 PDF Abstract BibTeX arXiv:2408.15332

Code (1)

shehper/AC-Solver 공식 구현 pytorch

Tasks

MathReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

What Makes Math Word Problems Challenging for LLMs?

2024-03-17 · KV Aditya Srivatsa, Ekaterina Kochmar

This paper investigates the question of what makes math word problems (MWPs) in English challenging for large language models (LLMs). We conduct an in-depth analysis of the key linguistic and mathematical characteristics…

Math

Peano: Learning Formal Mathematical Reasoning

2022-11-29 · Gabriel Poesia, Noah D. Goodman

General mathematical reasoning is computationally undecidable, but humans routinely solve new problems. Moreover, discoveries developed over centuries are taught to subsequent generations quickly. What structure enables …

Automated Theorem ProvingMathematical Reasoningvalid

Reinforcement Learning Assisted Recursive QAOA

2022-07-13 · Yash J. Patel, Sofiene Jerbi, Thomas Bäck, Vedran Dunjko

Variational quantum algorithms such as the Quantum Approximation Optimization Algorithm (QAOA) in recent years have gained popularity as they provide the hope of using NISQ devices to tackle hard combinatorial optimizati…

Combinatorial Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Bad-Policy Density: A Measure of Reinforcement Learning Hardness

2021-10-07 · David Abel, Cameron Allen, Dilip Arumugam, D. Ellis Hershkowitz 외

Reinforcement learning is hard in general. Yet, in many specific environments, learning is easy. What makes learning easy in one environment, but difficult in another? We address this question by proposing a simple measu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions

2022-11-16 · Zhening Li, Gabriel Poesia, Omar Costilla-Reyes, Noah Goodman 외

Humans tame the complexity of mathematical reasoning by developing hierarchies of abstractions. With proper abstractions, solutions to hard problems can be expressed concisely, thus making them more likely to be found. I…

LEMMAMathematical ReasoningVocal Bursts Intensity Prediction