Action Schema Networks: Generalised Policies with Deep Learning
By Sam Toyer, Felipe W. Trevizan, Sylvie Thiébaux, Lexing Xie. 2017
92 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Sergey Levine
- Ruslan Salakhutdinov
- Quoc V. Le
- Mohit Bansal
- Jianfeng Gao
- Kyunghyun Cho
- Josh Tenenbaum
Citations in the corpus
- Learning First-Order Symbolic Representations for Planning from the Structure of the State Space (2019, background): “More recently, general policies have been learned using deep learning methods but also starting with PDDL models [36, 9, 22, 6].”
- Relational inductive biases, deep learning, and graph networks (2018, methodology): “Similarly, Toyer et al. (2017) showed generalization to different sizes of planning problems, and Hamilton et al. (2017) showed generalization to producing useful node embeddings for previously unseen data.”
- Training Deep Reactive Policies for Probabilistic Planning Problems (2018, background): “Most recently, concurrent work (Toyer et al. 2018) is the first to learn deep networks for relational generalization across problems of PPDDL planning domains.”
- Deep Reactive Policies for Planning in Stochastic Nonlinear Domains (2019, background): “Currently, most works on DRPs in model-known planning have focused on discrete stochastic policies (Issakkimuthu, Fern, and Tadepalli 2018; Toyer et al. 2018; Groshev et al. 2018).”