Generalized Planning for the Abstraction and Reasoning Corpus

• URL: http://arxiv.org/abs/2401.07426v1
• Date: Mon, 15 Jan 2024 02:25:00 GMT
• Title: Generalized Planning for the Abstraction and Reasoning Corpus
• Authors: Chao Lei, Nir Lipovetzky, Krista A. Ehinger
• Abstract summary: We introduce an ARC solver, Generalized Planning for Abstract Reasoning (GPAR) It casts an ARC problem as a generalized planning (GP) problem, where a solution is formalized as a planning program with pointers. We show how to scale up GP solvers via domain knowledge specific to ARC in the form of restrictions over the actions model, predicates, arguments and valid structure of planning programs.
• Score: 10.377424252002795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that poses difficulties for pure machine learning methods due to its requirement for fluid intelligence with a focus on reasoning and abstraction. In this work, we introduce an ARC solver, Generalized Planning for Abstract Reasoning (GPAR). It casts an ARC problem as a generalized planning (GP) problem, where a solution is formalized as a planning program with pointers. We express each ARC problem using the standard Planning Domain Definition Language (PDDL) coupled with external functions representing object-centric abstractions. We show how to scale up GP solvers via domain knowledge specific to ARC in the form of restrictions over the actions model, predicates, arguments and valid structure of planning programs. Our experiments demonstrate that GPAR outperforms the state-of-the-art solvers on the object-centric tasks of the ARC, showing the effectiveness of GP and the expressiveness of PDDL to model ARC problems. The challenges provided by the ARC benchmark motivate research to advance existing GP solvers and understand new relations with other planning computational models. Code is available at github.com/you68681/GPAR.

Related papers

• Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation [65.23793829741014]
  Embodied-RAG is a framework that enhances the model of an embodied agent with a non-parametric memory system. At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail. We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 200 explanation and navigation queries.
  arXiv  Detail & Related papers  (2024-09-26T21:44:11Z)
• Planning with OWL-DL Ontologies (Extended Version) [6.767885381740952]
  We present a black-box that supports the full power expressive DL. Our main algorithm relies on rewritings of the OWL-mediated planning specifications into PDDL. We evaluate our implementation on benchmark sets from several domains.
  arXiv  Detail & Related papers  (2024-08-14T13:27:02Z)
• Towards Learning Abductive Reasoning using VSA Distributed Representations [56.31867341825068]
  We introduce the Abductive Rule Learner with Context-awareness (ARLC) model. ARLC features a novel and more broadly applicable training objective for abductive reasoning. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge.
  arXiv  Detail & Related papers  (2024-06-27T12:05:55Z)
• Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus [1.9662978733004604]
  The Abstraction and Reasoning Corpus (ARC) is unsolvable by any Machine Learning method. We propose a Program Synthesis system that uses Inductive Logic Programming (ILP), a branch of AI, to solve ARC.
  arXiv  Detail & Related papers  (2024-05-10T11:22:31Z)
• Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning [83.41487567765871]
  Skipper is a model-based reinforcement learning framework. It automatically generalizes the task given into smaller, more manageable subtasks. It enables sparse decision-making and focused abstractions on the relevant parts of the environment.
  arXiv  Detail & Related papers  (2023-09-30T02:25:18Z)
• When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
  We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
  arXiv  Detail & Related papers  (2023-08-29T17:22:39Z)
• LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations [50.431003245201644]
  We show that GPT-4 is unable to "reason" perfectly within non-language domains such as the 1D-ARC or a simple ARC subset. We propose an object-based representation that is obtained through an external tool, resulting in nearly doubling the performance on solved ARC tasks and near-perfect scores on the easier 1D-ARC.
  arXiv  Detail & Related papers  (2023-05-26T16:32:17Z)
• Learning Rational Subgoals from Demonstrations and Instructions [71.86713748450363]
  We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT.
  arXiv  Detail & Related papers  (2023-03-09T18:39:22Z)
• Abstract Visual Reasoning Enabled by Language [8.627180519837657]
  We propose a general learning-based framework for solving ARC. It is centered on transforming tasks from the vision to the language domain. This composition of language and vision allows for pre-trained models to be leveraged at each stage.
  arXiv  Detail & Related papers  (2023-03-07T17:52:46Z)
• Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus [19.27379168184259]
  The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it impossible to solve using pure machine learning. We propose Abstract Reasoning with Graph Abstractions (ARGA), a new object-centric framework that first represents images using graphs and then performs a search for a correct program.
  arXiv  Detail & Related papers  (2022-10-18T14:13:43Z)

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.