mlsanityData to 14 Oct 2026

Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module

arXiv 2112.07222 ↗First posted 14 Dec 2021cs.LG cs.AI cs.MAcited by 1

Not on the map. Why?

Abstract (arXiv)

Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios. To this end, a multi-agent framework needs to handle various scenarios of agents, in terms of both scales and dynamics, for being practical to real-world applications. We formulate the multi-agent environment with a different number of agents as a multi-tasking problem and propose a meta reinforcement learning (meta-RL) framework to tackle this problem. The proposed framework employs a meta-learned Communication Pattern Recognition (CPR) module to identify communication behavior and extract information that facilitates the training process. Experimental results are poised to demonstrate that the proposed framework (a) generalizes to an unseen larger number of agents and (b) allows the number of agents to change between episodes. The ablation study is also provided to reason the proposed CPR design and show such design is effective.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 50 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

42 of 50 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  9. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  10. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  11. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  12. 2016Deep Variational Information Bottleneckcited by 930
30 more
  1. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  2. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  3. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  4. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  5. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  6. 2016Learning Multiagent Communication with Backpropagationcited by 366
  7. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  8. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  9. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  10. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 261
  11. 2017Learning with Opponent-Learning Awarenesscited by 222
  12. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  13. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
  14. 2020Multi-Task Reinforcement Learning with Soft Modularizationcited by 143
  15. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 121
  16. 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 108
  17. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  18. 2019Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularitycited by 70
  19. 2019Meta-Q-Learningcited by 62
  20. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  21. 2020Multi-agent Reinforcement Learning for Networked System Controlcited by 53
  22. 2020Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learningcited by 48
  23. 2018DiCE: The Infinitely Differentiable Monte-Carlo Estimatorcited by 46
  24. 2020A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learningcited by 41
  25. 2020Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learningcited by 38
  26. 2019From Few to More: Large-scale Dynamic Multiagent Curriculum Learningcited by 36
  27. 2019MetaFun: Meta-Learning with Iterative Functional Updatescited by 34
  28. 2021Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Compositioncited by 30
  29. 2019Watch, Try, Learn: Meta-Learning from Demonstrations and Rewardcited by 28
  30. 2021Toward Robust Long Range Policy Transfercited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022CLA-NeRF: Category-Level Articulated Neural Radiance Fieldcited by 56