Scholarlink

Goal Recognition (GR) consists of recognising the goal of an agent from partial observations. The state of the art on particular planning domains is represented by GRNet, a model based on Recurrent Neural Networks that solves GR as a classification task. Compared to automated planning, the need for large training sets is the main disadvantage of these approaches. Therefore, we formalise a loss regularisation technique to reduce the number of training samples needed, to reduce the convergence time, and to increase the performance in GR instances with a small percentage of observations. We empirically evaluate its effectiveness through extensive experiments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Regularised Loss Function for Goal Recognition as a Deep Learning Task

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Matteo Olivato,
  • Mattia Chiari,
  • Lorenzo Serina,
  • Valerio Borelli,
  • Massimiliano Tummolo,
  • Ivan Serina,
  • Nicholas Rossetti,
  • Alfonso Emilio Gerevini

摘要

Goal Recognition (GR) consists of recognising the goal of an agent from partial observations. The state of the art on particular planning domains is represented by GRNet, a model based on Recurrent Neural Networks that solves GR as a classification task. Compared to automated planning, the need for large training sets is the main disadvantage of these approaches. Therefore, we formalise a loss regularisation technique to reduce the number of training samples needed, to reduce the convergence time, and to increase the performance in GR instances with a small percentage of observations. We empirically evaluate its effectiveness through extensive experiments.