We present the first approach capable of learning domain-independent planning heuristics
entirely from scratch. The heuristics we learn map the hypergraph representation of the …

In this paper, we discuss the learning of generalised policies for probabilistic and classical
planning problems using Action Schema Networks (ASNets). The ASNet is a neural network …

Abstract A Relational Markov Decision Process (RMDP) is a first-order representation to
express all instances of a single probabilistic planning domain with possibly unbounded …

Reinforcement learning in problems with symbolic state spaces is challenging due to the
need for reasoning over long horizons. This paper presents a new approach that utilizes …

How can we train neural network (NN) heuristic functions for classical planning, using only
states as the NN input? Prior work addressed this question by (a) per-instance imitation …

There is a recent focus on designing architectures that have an Integer Linear Programming
(ILP) layer within a neural model (referred to as\emph {Neural ILP} in this paper). Neural ILP …

We focus on reinforcement learning (RL) in relational problems that are naturally defined in
terms of objects, their relations, and manipulations. These problems are characterized by …

Testing is a promising way to gain trust in a learned action policy π, in particular if π is a
neural network. A “bug” in this context constitutes undesirable or fatal policy behavior, eg …

Can an asset manager plan the optimal timing for her/his hedging strategies given market
conditions? The standard approach based on Markowitz or other more or less sophisticated …

Current approaches for learning for planning have yet to achieve competitive performance
against classical planners in several domains, and have poor overall performance. In this …