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 variable state and action spaces, and
finding a fixed-length representation, required by most existing RL methods, is
difficult, if not impossible. We present a deep RL framework based on graph
neural networks and auto-regressive policy decomposition that naturally works
with these problems and is completely domain-independent. We demonstrate the
framework in three very distinct domains and we report the method's competitive
performance and impressive zero-shot generalization over different problem
sizes. In goal-oriented BlockWorld, we demonstrate multi-parameter actions with
pre-conditions. In SysAdmin, we show how to select multiple objects
simultaneously. In the classical planning domain of Sokoban, the method trained
exclusively on 10x10 problems with three boxes solves 89% of 15x15 problems
with five boxes.

通过图神经网络和自回归策略分解，构建了一个深度强化学习框架，在多样化场景下表现出了出色的竞争能力和卓越的零 - shot 泛化能力.