Learning Generalized Reactive Policies Using Deep Neural Networks


  • Edward Groshev University of California, Berkeley
  • Maxwell Goldstein Princeton University
  • Aviv Tamar University of California, Berkeley
  • Siddharth Srivastava Arizona State University
  • Pieter Abbeel University of California, Berkeley




learning for planning, deep neural networks, generalized reactive policy, learned heuristic, imitation learning


We present a new approach to learning for planning, where knowledge acquired while solving a given set of planning problems is used to plan faster in related, but new problem instances. We show that a deep neural network can be used to learn and represent a generalized reactive policy (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances. In contrast to prior efforts in this direction, our approach significantly reduces the dependence of learning on handcrafted domain knowledge or feature selection. Instead, the GRP is trained from scratch using a set of successful execution traces. We show that our approach can also be used to automatically learn a heuristic function that can be used in directed search algorithms. We evaluate our approach using an extensive suite of experiments on two challenging planning problem domains and show that our approach facilitates learning complex decision making policies and powerful heuristic functions with minimal human input.




How to Cite

Groshev, E., Goldstein, M., Tamar, A., Srivastava, S., & Abbeel, P. (2018). Learning Generalized Reactive Policies Using Deep Neural Networks. Proceedings of the International Conference on Automated Planning and Scheduling, 28(1), 408-416. https://doi.org/10.1609/icaps.v28i1.13872