Generalized Planning With Deep Reinforcement Learning
arXiv:2005.02305
Abstract
A hallmark of intelligence is the ability to deduce general principles from examples, which are correct beyond the range of those observed. Generalized Planning deals with finding such principles for a class of planning problems, so that principles discovered using small instances of a domain can be used to solve much larger instances of the same domain. In this work we study the use of Deep Reinforcement Learning and Graph Neural Networks to learn such generalized policies and demonstrate that they can generalize to instances that are orders of magnitude larger than those they were trained on.
13 pages
References in corpus (5)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The FF Planning System: Fast Plan Generation Through Heuristic Search
- Action Schema Networks: Generalised Policies with Deep Learning
- Learning Domain-Independent Planning Heuristics with Hypergraph Networks
- Learning to Rank for Synthesizing Planning Heuristics