Graph Convolutional Memory using Topological Priors

Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the first hybrid memory model for solving POMDPs using reinforcement learning. GCM uses either human-defined or data-driven topological priors to form graph neighborhoods, combining them into a larger network topology using dynamic programming. We query the graph using graph convolution, coalescing relevant memories into a context-dependent belief. When used without human priors, GCM performs similarly to state-of-the-art methods. When used with human priors, GCM outperforms these methods on control, memorization, and navigation tasks while using significantly fewer parameters.