Jul 17, 2022 · We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for ...
Our method takes many samples from each pre-image found in a regression, instead of per- forming many trajectories or longer regressions to increase the number ...
Oct 22, 2024 · We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for ...
Jul 7, 2022 · Our experimental study shows that RSL outperforms, in terms of coverage, previous classical planning NN heuristics functions while requiring two ...
Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning · Computer Science. J. Artif. Intell. Res. · 2024.
Missing: (Extended | Show results with:(Extended
Our experimental study shows that RSL outperforms, in terms of coverage, previous classical planning NN heuristics functions while requiring two orders of ...
Missing: (Extended | Show results with:(Extended
Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning (Extended Abstract). SOCS 2022: 308-310. [i2]. view. electronic edition via DOI ...
FSM is a learning-based planner that uses different sample generation improvement strategies to learn a heuristic func- tion for classical planning.
Missing: (Extended | Show results with:(Extended
We study the problem of learning good heuristic functions for classical planning tasks with neural networks based on samples represented by states with their ...
Missing: (Extended | Show results with:(Extended
Oct 7, 2024 · Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning (Extended Abstract). SOCS 2022: 308-310. [i6]. view. electronic ...