Contrastive Reinforcement Learning of Symbolic Reasoning Domains

• URL: http://arxiv.org/abs/2106.09146v1
• Date: Wed, 16 Jun 2021 21:46:07 GMT
• Title: Contrastive Reinforcement Learning of Symbolic Reasoning Domains
• Authors: Gabriel Poesia, WenXin Dong, Noah Goodman
• Abstract summary: Learning to solve symbolic problems is challenging for machine learning algorithms. Existing models either learn from human solutions or use hand-engineered features, making them expensive to apply in new domains. In this paper, we consider symbolic domains as simple environments where states and actions are given as unstructured text, and binary rewards indicate whether a problem is solved.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Abstract symbolic reasoning, as required in domains such as mathematics and logic, is a key component of human intelligence. Solvers for these domains have important applications, especially to computer-assisted education. But learning to solve symbolic problems is challenging for machine learning algorithms. Existing models either learn from human solutions or use hand-engineered features, making them expensive to apply in new domains. In this paper, we instead consider symbolic domains as simple environments where states and actions are given as unstructured text, and binary rewards indicate whether a problem is solved. This flexible setup makes it easy to specify new domains, but search and planning become challenging. We introduce four environments inspired by the Mathematics Common Core Curriculum, and observe that existing Reinforcement Learning baselines perform poorly. We then present a novel learning algorithm, Contrastive Policy Learning (ConPoLe) that explicitly optimizes the InfoNCE loss, which lower bounds the mutual information between the current state and next states that continue on a path to the solution. ConPoLe successfully solves all four domains. Moreover, problem representations learned by ConPoLe enable accurate prediction of the categories of problems in a real mathematics curriculum. Our results suggest new directions for reinforcement learning in symbolic domains, as well as applications to mathematics education.

Related papers

• Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems [12.990207889359402]
  Pathfinding problems are found in robotics, computational science, and natural sciences. Traditional methods to solve these require training deep neural networks (DNNs) for each new problem domain. This study introduces a novel foundation model, leveraging deep reinforcement learning to train functions that seamlessly adapt to new domains.
  arXiv  Detail & Related papers  (2024-06-01T16:18:20Z)
• Symbolic Equation Solving via Reinforcement Learning [9.361474110798143]
  We propose a novel deep-learning interface involving a reinforcement-learning agent that operates a symbolic stack calculator. By construction, this system is capable of exact transformations and immune to hallucination.
  arXiv  Detail & Related papers  (2024-01-24T13:42:24Z)
• A Survey of Deep Learning for Mathematical Reasoning [71.88150173381153]
  We review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. Recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning.
  arXiv  Detail & Related papers  (2022-12-20T18:46:16Z)
• Peano: Learning Formal Mathematical Reasoning [35.086032962873226]
  General mathematical reasoning is computationally undecidable, but humans routinely solve new problems. We posit that central to both puzzles is the structure of procedural abstractions underlying mathematics. We explore this idea in a case study on 5 sections of beginning algebra on the Khan Academy platform.
  arXiv  Detail & Related papers  (2022-11-29T01:42:26Z)
• JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding [74.12405417718054]
  This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model(PLM) Unlike other standard NLP tasks, mathematical texts are difficult to understand, since they involve mathematical terminology, symbols and formulas in the problem statement. We design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
  arXiv  Detail & Related papers  (2022-06-13T17:03:52Z)
• On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
  Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
  arXiv  Detail & Related papers  (2022-03-08T09:57:48Z)
• SMART: A Situation Model for Algebra Story Problems via Attributed Grammar [74.1315776256292]
  We introduce the concept of a emphsituation model, which originates from psychology studies to represent the mental states of humans in problem-solving. We show that the proposed model outperforms all previous neural solvers by a large margin while preserving much better interpretability.
  arXiv  Detail & Related papers  (2020-12-27T21:03:40Z)
• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence [48.67755344239951]
  We provide a comprehensive survey, and propose a new taxonomy for localization and mapping using deep learning. A wide range of topics are covered, from learning odometry estimation, mapping, to global localization and simultaneous localization and mapping. It is our hope that this work can connect emerging works from robotics, computer vision and machine learning communities.
  arXiv  Detail & Related papers  (2020-06-22T19:01:21Z)
• Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [95.18337034090648]
  We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG) These visual arithmetic problems are in the form of geometric figures. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
  arXiv  Detail & Related papers  (2020-04-25T17:14:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.