While routing in wireless networks has been studied extensively, existing protocols are typically designed for a specific set of network conditions and so do not easily accommodate changes in those conditions. For instance, protocols that assume network connectivity cannot be easily applied to disconnected networks. In this paper, we develop a distributed routing strategy based on deep reinforcement learning that generalizes to diverse traffic patterns, congestion levels, network connectivity, and link dynamics. We make the following key innovations in our design: (i) the use of relational features as inputs to the deep neural network approximating the decision space, which enables our algorithm to generalize to diverse network conditions, (ii) the use of packet-centric decisions to transform the routing problem into an episodic task by viewing packets, rather than wireless devices, as reinforcement learning agents, which provides a natural way to propagate and model rewards accurately during learning, and (iii) the use of extended-time actions to model the time spent by a packet waiting in a queue, which reduces the amount of training data needed and allows the learning algorithm to converge more quickly. We evaluate our routing algorithm using a packet-level simulator and show that the policy our algorithm learns during training is able to generalize to larger and more congested networks, different topologies, and diverse link dynamics. Our algorithm outperforms shortest path and backpressure routing with respect to packets delivered and delay per packet.

We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition graphs---those that are constructed using only the most recent experiences of the agent. The local scope of our subgoal discovery method allows it to successfully identify the type of subgoals we seek---states that lie between two densely-connected regions of the state space while producing an algorithm with low computational cost.

Abstract We present an overview of the Common Component Architecture (CCA) core specification and CCAFFEINE, a Sandia National Laboratories framework implementation compliant with the draft specification. CCAFFEINE stands for CCA Fast Framework Example In Need of Everything; that is, CCAFFEINE is fast, lightweight, and it aims to provide every framework service by using external, portable components instead of integrating all services into a single, heavy framework core. By fast, we mean that the CCAFFEINE glue does not get between components in a way that slows down their interactions. We present the CCAFFEINE solutions to several fundamental problems in the application of component software approaches to the construction of single program multiple data (SPMD) applications. We demonstrate the integration of components from three organizations, two within Sandia and one at Oak Ridge National Laboratory. We outline some requirements for key enabling facilities needed for a successful component approach to SPMD application building. Copyright © 2002 John Wiley & Sons, Ltd.