mlsanityData to 7 Oct 2026

Amortized Network Intervention to Steer the Excitatory Point Processes

arXiv 2310.04159 ↗First posted 6 Oct 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Excitatory point processes (i.e., event flows) occurring over dynamic graphs (i.e., evolving topologies) provide a fine-grained model to capture how discrete events may spread over time and space. How to effectively steer the event flows by modifying the dynamic graph structures presents an interesting problem, motivated by curbing the spread of infectious diseases through strategically locking down cities to mitigating traffic congestion via traffic light optimization. To address the intricacies of planning and overcome the high dimensionality inherent to such decision-making problems, we design an Amortized Network Interventions (ANI) framework, allowing for the pooling of optimal policies from history and other contexts while ensuring a permutation equivalent property. This property enables efficient knowledge transfer and sharing across diverse contexts. Each task is solved by an H-step lookahead model-based reinforcement learning, where neural ODEs are introduced to model the dynamics of the excitatory point processes. Instead of simulating rollouts from the dynamics model, we derive an analytical mean-field approximation for the event flows given the dynamics, making the online planning more efficiently solvable. We empirically illustrate that this ANI approach substantially enhances policy learning for unseen dynamics and exhibits promising outcomes in steering event flows through network intervention using synthetic and real COVID datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 6 Oct 2023.

Builds on

36 of 52 references.

References · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  5. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  6. 2018World Modelscited by 1,444
  7. 2023Mastering Diverse Domains through World Modelscited by 1,193
  8. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  11. 2018Neural Processescited by 307
  12. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
24 more
  1. 2019Neural Jump Stochastic Differential Equationscited by 147
  2. 2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
  3. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 128
  4. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  5. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  6. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 97
  7. 2020Neural Spatio-Temporal Point Processescited by 92
  8. 2019Reparameterizable Subset Sampling via Continuous Relaxationscited by 69
  9. 2020STEER: Simple Temporal Regularization For Neural ODEscited by 58
  10. 2021The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learningcited by 50
  11. 2019PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learningcited by 46
  12. 2020"Hey, that's not an ODE": Faster ODE Adjoints via Seminormscited by 35
  13. 2018Deep Reinforcement Learning of Marked Temporal Point Processescited by 32
  14. 2020Model-based Adversarial Meta-Reinforcement Learningcited by 32
  15. 2020Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networkscited by 30
  16. 2017Fake News Mitigation via Point Process Based Interventioncited by 24
  17. 2022Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processescited by 23
  18. 2020Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learningcited by 19
  19. 2021Model-based Meta Reinforcement Learning using Graph Structured Surrogate Modelscited by 16
  20. 2014Shaping Social Activity by Incentivizing Userscited by 15
  21. 2020Latent Network Structure Learning from High Dimensional Multivariate Point Processescited by 12
  22. 2020Group Network Hawkes Processcited by 7
  23. 2020Learning Multivariate Hawkes Processes at Scalecited by 5
  24. 2020Quarantines as a Targeted Immunization Strategycited by 1

Built on by

Not cited yet.