0
点赞
收藏
分享

微信扫一扫

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

在这里插入图片描述

Motivation

  • Significance:
    MARL is useful for many real-world applications, sensor networks, traffic management, coordinate robots, etc.
  • Problems:
    Hard to learn effective policies in complex multi-agent scenarios, and action-obs space grows largely with number of agents. And PDSP (policy decentralization with shared params) is used to solve scalability problem.

But for PSDP, the drawback is: tasks usually require diversified policies among agents, while shared params lead to similar behaviors(under similar obs).

A tradeoff: sharing necessary params to accelerate learning while improve diversity.

  • Keywords:
    MARL, PDSP, tradeoff

 Backgrounds:
Dec-POMDP(Decentralized partially observable MDP), CTDE, IGM,

 Model

  • Structure:
    diversity-driven MARL framework
  • Theory:
    Maximation of information-theoretic objective
    Action-Value Learning for Balancing Diversity and Sharing
    Overall Learning Objective

 Experiment

  • Metrics:
  • Benchmark tasks & Baselines:
    Google Research Football(GRF), StarCraft II micro-management(SMAC)
    CDS(proposed), QPLEX, QMIX, MAVEN, EOI
  • Design:
    Demonstration of how the approach works.
  • Conclusion:
    State-of-art result.

 Thinking

  • Pros:
     A novel mechanism of being diverse when necessary into shared multi-agent reinforcement learning
     The balance between individual diversity and group coordination
  • Cros:
    No ablation studies shown and more explanation about L1 not shown

Links:
Video: https://sites.google.com/view/celebrate-diversity-shared
Code: https://github.com/lich14/CDS

举报

相关推荐

0 条评论