no code implementations • 25 Mar 2024 • Dillon Z. Chen, Felipe Trevizan, Sylvie Thiébaux
Current approaches for learning for planning have yet to achieve competitive performance against classical planners in several domains, and have poor overall performance.
no code implementations • 26 Jan 2024 • Johannes Schmalz, Felipe Trevizan
Current methods for solving Stochastic Shortest Path Problems (SSPs) find states' costs-to-go by applying Bellman backups, where state-of-the-art methods employ heuristics to select states to back up and prune.
no code implementations • 18 Dec 2023 • Dillon Z. Chen, Sylvie Thiébaux, Felipe Trevizan
We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search.
no code implementations • 25 Mar 2023 • Dillon Chen, Felipe Trevizan, Sylvie Thiébaux
Heuristic search is a powerful approach that has successfully been applied to a broad class of planning problems, including classical planning, multi-objective planning, and probabilistic planning modelled as a stochastic shortest path (SSP) problem.
no code implementations • 29 Nov 2019 • William Shen, Felipe Trevizan, Sylvie Thiébaux
We present the first approach capable of learning domain-independent planning heuristics entirely from scratch.
1 code implementation • 4 Aug 2019 • Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie
In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets).
1 code implementation • 13 Sep 2017 • Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie
In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems.
no code implementations • 30 Jun 2017 • Peter Baumgartner, Sylvie Thiébaux, Felipe Trevizan
Policy synthesis addresses the problem of how to control or limit the decisions an agent makes so that a given specification is met.
no code implementations • NeurIPS 2012 • Felipe Trevizan, Manuela Veloso
In order to compute a solution for a probabilistic planning problem, planners need to manage the uncertainty associated with the different paths from the initial state to a goal state.