NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems

• URL: http://arxiv.org/abs/2301.10280v2
• Date: Tue, 16 Jul 2024 17:37:41 GMT
• Title: NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems
• Authors: Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares,
• Abstract summary: We propose Ne SIG, to the best of our knowledge, the first domain-independent method for automatically generating planning problems. We formulate problem generation as a Markov Decision Process and train two generative policies with Deep Reinforcement Learning to generate problems. Results show Ne SIG is able to automatically generate valid and diverse problems of much greater difficulty than domain-specific generators.
• Score: 9.176056742068814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the field of Automated Planning there is often the need for a set of planning problems from a particular domain, e.g., to be used as training data for Machine Learning or as benchmarks in planning competitions. In most cases, these problems are created either by hand or by a domain-specific generator, putting a burden on the human designers. In this paper we propose NeSIG, to the best of our knowledge the first domain-independent method for automatically generating planning problems that are valid, diverse and difficult to solve. We formulate problem generation as a Markov Decision Process and train two generative policies with Deep Reinforcement Learning to generate problems with the desired properties. We conduct experiments on three classical domains, comparing our approach against handcrafted, domain-specific instance generators and various ablations. Results show NeSIG is able to automatically generate valid and diverse problems of much greater difficulty (15.5 times more on geometric average) than domain-specific generators, while simultaneously reducing human effort when compared to them. Additionally, it can generalize to larger problems than those seen during training.

Related papers

• Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems [61.26070215983157]
  We introduce the term EFA (Executable Functional Abstraction) to denote such programs for math problems. EFA-like constructs have been shown to be useful for math reasoning as problem generators for stress-testing models. We explore the automatic construction of EFAs for advanced math problems.
  arXiv  Detail & Related papers  (2025-04-14T00:06:48Z)
• LLM-Generated Heuristics for AI Planning: Do We Even Need Domain-Independence Anymore? [87.71321254733384]
  Large language models (LLMs) can generate planning approaches tailored to specific planning problems. LLMs can achieve state-of-the-art performance on some standard IPC domains. We discuss whether these results signify a paradigm shift and how they can complement existing planning approaches.
  arXiv  Detail & Related papers  (2025-01-30T22:21:12Z)
• AutoG: Towards automatic graph construction from tabular data [60.877867570524884]
  We aim to formalize the graph construction problem and propose an effective solution. Existing automatic construction methods can only be applied to some specific cases. We present a set of datasets to formalize and evaluate graph construction methods. Second, we propose an LLM-based solution, AutoG, automatically generating high-quality graph schemas.
  arXiv  Detail & Related papers  (2025-01-25T17:31:56Z)
• Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator [33.680619900836376]
  We propose a pipeline to solve the domain-specific calculation problems with Knowledge-Intensive Programs Generator. It generates knowledge-intensive programs according to the domain-specific documents. We also find that the code generator is also adaptable to other domains, without training on the new knowledge.
  arXiv  Detail & Related papers  (2024-12-12T13:42:58Z)
• Multi-agent Planning using Visual Language Models [2.2369578015657954]
  Large Language Models (LLMs) and Visual Language Models (VLMs) are attracting increasing interest due to their improving performance and applications across various domains and tasks. LLMs andVLMs can produce erroneous results, especially when a deep understanding of the problem domain is required. We propose a multi-agent architecture for embodied task planning that operates without the need for specific data structures as input.
  arXiv  Detail & Related papers  (2024-08-10T08:10:17Z)
• Contractual Reinforcement Learning: Pulling Arms with Invisible Hands [68.77645200579181]
  We propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation.
  arXiv  Detail & Related papers  (2024-07-01T16:53:00Z)
• PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models [10.491051578439722]
  We propose the idea of programming problem merging (PPM) and provide two implementation of this idea, we utilize our tool on two widely-used datasets. The results demonstrate the effectiveness of our tool in generating more challenging, diverse, and natural programming problems.
  arXiv  Detail & Related papers  (2024-01-28T02:27:38Z)
• Automated Process Planning Based on a Semantic Capability Model and SMT [50.76251195257306]
  In research of manufacturing systems and autonomous robots, the term capability is used for a machine-interpretable specification of a system function. We present an approach that combines these two topics: starting from a semantic capability model, an AI planning problem is automatically generated.
  arXiv  Detail & Related papers  (2023-12-14T10:37:34Z)
• Large Language Models as Analogical Reasoners [155.9617224350088]
  Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks. We introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models.
  arXiv  Detail & Related papers  (2023-10-03T00:57:26Z)
• The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning [80.1018596899899]
  We argue that neural network models share this same preference, formalized using Kolmogorov complexity. Our experiments show that pre-trained and even randomly language models prefer to generate low-complexity sequences. These observations justify the trend in deep learning of unifying seemingly disparate problems with an increasingly small set of machine learning models.
  arXiv  Detail & Related papers  (2023-04-11T17:22:22Z)
• Graph-Based Specification and Automated Construction of ILP Problems [0.0]
  We introduce the GIPS (Graph-Based ILP Problem Specification Tool) framework that simplifies the development of ILP problem generators. Our approach uses GIPSL specifications as a starting point to derive ILP problem generators for a specific application domain automatically. First experiments show that the derived ILP problem generators can compete with hand-crafted programs developed by ILP experts.
  arXiv  Detail & Related papers  (2022-12-22T11:52:35Z)
• OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics [124.08684545010664]
  Scene graph generation from images is a task of great interest to applications such as robotics. We propose an initial approximation to a framework called Ontology-Guided Scene Graph Generation (OG-SGG)
  arXiv  Detail & Related papers  (2022-02-21T13:23:15Z)
• An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents [1.3812010983144802]
  We propose a deep reinforcement learning methodology for the job shop scheduling problem (JSSP) The aim is to build up a greedy-like able to learn on some distribution of JSSP instances, different in the number of jobs and machines. As expected, the model can generalize, to some extent, to larger problems or instances originated by a different distribution from the one used in training.
  arXiv  Detail & Related papers  (2021-10-18T07:55:39Z)
• GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning [172.36214872466707]
  We focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams, and theorem knowledge. We propose a Geometric Question Answering dataset GeoQA, containing 5,010 geometric problems with corresponding annotated programs.
  arXiv  Detail & Related papers  (2021-05-30T12:34:17Z)
• Exploring Instance Generation for Automated Planning [1.6735240552964108]
  Constraint programming and automated planning are examples of these areas. The efficiency of each solving method varies not only between problems, but also between instances of the same problem. We propose a new approach where the whole planning problem description is modelled using Essence.
  arXiv  Detail & Related papers  (2020-09-21T19:58:33Z)

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.