In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By mimicking the relational structure of planning problems, ASNets are able to adopt a weight-sharing scheme which allows the network to be applied to any problem from a given planning domain. This allows the cost of training the network to be amortised over all problems in that domain. Further, we propose a training method which balances exploration and supervised training on small problems to produce a policy which remains robust when evaluated on larger problems. In experiments, we show that ASNet's learning capability allows it to significantly outperform traditional non-learning planners in several challenging domains.

介绍了Action Schema Network(ASNet)：一种用于学习概率规划问题通用策略的神经网络模型。通过模拟规划问题的关系结构，ASNet能够采用权重共享方案，使网络能够应用于给定规划域中的任何问题。此外，提出一种平衡探索和监督训练的训练方法，以产生在评估较大问题时仍保持稳健的策略。在实验中，我们展示了ASNet的学习能力让其在多个具有挑战性的领域中明显优于传统的非学习规划者。

行动模式网络：深度学习的广义策略