Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

Abstract

We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications. Our approach is to learn local controllers that require only local information and communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, we learn a single common local controller which exploits information from distant teammates using only local communication interchanges. We apply this approach to the problem of flocking to demonstrate performance on communication graphs that change as the robots move. We examine how a decreasing communication radius and faster velocities increase the value of multi-hop information.

References in corpus (52)

• Learning Transferable Features with Deep Adaptation Networks
• Spectral Networks and Locally Connected Networks on Graphs
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Brownian distance covariance
• Discrete Signal Processing on Graphs: Sampling Theory
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Domain Generalization via Invariant Feature Representation
• Generative Moment Matching Networks
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• UAV-Assisted Heterogeneous Networks for Capacity Enhancement
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Distinguishing cause from effect using observational data: methods and benchmarks
• Kernel dimension reduction in regression
• Sampling of graph signals with successive local aggregations
• Stability Properties of Graph Neural Networks
• Training generative neural networks via Maximum Mean Discrepancy optimization
• A Kernel Test of Goodness of Fit
• Learning from Distributions via Support Measure Machines
• Sharp analysis of low-rank kernel matrix approximations
• Density Estimation in Infinite Dimensional Exponential Families
• Kernel Belief Propagation
• Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions
• k-NN Regression Adapts to Local Intrinsic Dimension
• Testing for Homogeneity with Kernel Fisher Discriminant Analysis
• Relational Forward Models for Multi-Agent Learning
• Optimal Rates for Random Fourier Features
• FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
• A Test of Relative Similarity For Model Selection in Generative Models
• On the optimal estimation of probability measures in weak and strong topologies
• A Kernel Independence Test for Random Processes
• On the Error of Random Fourier Features
• Kernel Mean Shrinkage Estimators
• Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families
• Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering
• Kernel Adaptive Metropolis-Hastings
• Bayesian Quadratic Network Game Filters
• Optimally-Weighted Herding is Bayesian Quadrature
• A Kernel Test for Three-Variable Interactions
• A Wild Bootstrap for Degenerate Kernel Tests
• Herding Dynamic Weights for Partially Observed Random Field Models
• Convergence guarantees for kernel-based quadrature rules in misspecified settings
• Adaptivity and Computation-Statistics Tradeoffs for Kernel and Distance based High Dimensional Two Sample Testing
• Hilbert Space Embeddings of POMDPs
• Detecting low-complexity unobserved causes
• Testing Hypotheses by Regularized Maximum Mean Discrepancy
• Kernel Mean Estimation via Spectral Filtering
• Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders
• Characteristic Kernels and Infinitely Divisible Distributions
• Minimax Estimation of Kernel Mean Embeddings
• A low variance consistent test of relative dependency
• Nonparametric Independence Testing for Small Sample Sizes
• On a link between kernel mean maps and Fraunhofer diffraction, with an application to super-resolution beyond the diffraction limit

Cited by in corpus (58)

• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Deep transfer operator learning for partial differential equations under conditional shift
• Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces
• Kernel-based approximation of the Koopman generator and Schrödinger operator
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• Robust Domain Misinformation Detection via Multi-modal Feature Alignment
• Discovering and Deciphering Relationships Across Disparate Data Modalities
• A kernel-based approach to molecular conformation analysis
• Kernel methods for detecting coherent structures in dynamical data
• Anomaly Detection Based on Isolation Mechanisms: A Survey
• Distribution-based Sketching of Single-Cell Samples
• Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
• Learnware: Small Models Do Big
• Kernel method for persistence diagrams via kernel embedding and weight factor
• Nonequilibrium Statistical Mechanics and Optimal Prediction of Partially-Observed Complex Systems
• Supervised Learning with Quantum Measurements
• Automatic and effective discovery of quantum kernels
• Quantum Mean Embedding of Probability Distributions
• Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison
• Transparent Single-Cell Set Classification with Kernel Mean Embeddings
• Change Detection of Markov Kernels with Unknown Pre and Post Change Kernel
• Feature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models
• Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces
• Local Group Invariant Representations via Orbit Embeddings
• Distribution regression model with a Reproducing Kernel Hilbert Space approach
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Steganographer Identification
• When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
• Detecting Change Intervals with Isolation Distributional Kernel
• Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test
• Confidence-based Estimators for Predictive Performance in Model Monitoring
• Data-Driven Observability Analysis for Nonlinear Stochastic Systems
• Estimation of copulas via Maximum Mean Discrepancy
• Diffeological statistical models, the Fisher metric and probabilistic mappings
• Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method
• Learning Interpretable Collective Variables for Spreading Processes on Networks
• A Kernel Independence Test for Geographical Language Variation
• Testing and Learning on Distributions with Symmetric Noise Invariance
• Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces
• A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulation
• Towards a Kernel based Uncertainty Decomposition Framework for Data and Models
• Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach
• Approximating Symmetrized Estimators of Scatter via Balanced Incomplete U-Statistics
• Causal survival embeddings: non-parametric counterfactual inference under censoring
• Approximate Bayesian Computation Based on Maxima Weighted Isolation Kernel Mapping
• Model-Free Change Point Detection for Mixing Processes
• Reversible Gromov-Monge Sampler for Simulation-Based Inference
• Ergodic Trajectory Optimization on Generalized Domains Using Maximum Mean Discrepancy
• Fully symmetric kernel quadrature
• Revisiting RIP guarantees for sketching operators on mixture models
• Instrument Space Selection for Kernel Maximum Moment Restriction
• FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
• Signal reconstruction using determinantal sampling
• Generalization Analysis of Transformers in Distribution Regression
• Hyperparameter Learning for Conditional Kernel Mean Embeddings with Rademacher Complexity Bounds
• Minimum Discrepancy Methods in Uncertainty Quantification
• Nonlinear Distribution Regression for Remote Sensing Applications
• Composable Learning with Sparse Kernel Representations