提出三种去中心化强化学习算法，支持多智能体协作、对抗与混合场景。
Fully-Decentralized MADDPG with Networked Agents
- 通过网络化通信与代理策略实现训练去中心化
- 在多智能体数量增加时计算成本显著降低
- 适用于连续动作空间的协同与对抗任务
本文设计了三种适用于连续动作空间的去中心化训练多智能体强化学习算法，涵盖合作、对抗及混合场景。通过在MADDPG基础上引入智能体间网络化通信机制，并引入代理策略，在保持局部通信的同时实现训练去中心化。实验表明，去中心化算法在性能上可媲美原始MADDPG，且随着智能体数量增多，计算开销下降更明显。
原文摘要 · Abstract (English)
In this paper, we devise three actor-critic algorithms with decentralized training for multi-agent reinforcement learning in cooperative, adversarial, and mixed settings with continuous action spaces. To this goal, we adapt the MADDPG algorithm by applying a networked communication approach between agents. We introduce surrogate policies in order to decentralize the training while allowing for local communication during training. The decentralized algorithms achieve comparable results to the original MADDPG in empirical tests, while reducing computational cost. This is more pronounced with larger numbers of agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。