TY - JOUR AU - Toyer, Sam AU - Trevizan, Felipe AU - Thiébaux, Sylvie AU - Xie, Lexing PY - 2018/04/26 Y2 - 2024/03/29 TI - Action Schema Networks: Generalised Policies With Deep Learning JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 32 IS - 1 SE - Main Track: Planning and Scheduling DO - 10.1609/aaai.v32i1.12089 UR - https://ojs.aaai.org/index.php/AAAI/article/view/12089 SP - AB - <p> 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. </p> ER -