用近似行为度量投影提升联邦强化学习性能并保护隐私
Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning
- 通过学习客户端的状态投影函数，实现高效信息共享
- 在DeepMind控制套件上显著提升联邦强化学习效果
- 不共享敏感数据，适合隐私敏感的分布式智能场景
联邦强化学习（FRL）通常加密共享本地状态或策略信息，在保护隐私的同时促进各客户端间的学习。本文提出，共享基于近似行为度量的状态投影函数是提升FRL性能且有效保护敏感信息的可行方法。我们提出FedRAG框架，为每个客户端学习一个计算高效的投影函数，并在中央服务器聚合这些投影函数参数。该方法不共享任何任务特异性敏感信息，但能为各客户端带来信息增益。我们在DeepMind Control Suite上进行了大量实验，验证了其有效性。
原文摘要 · Abstract (English)
Federated reinforcement learning (FRL) methods usually share the encrypted local state or policy information and help each client to learn from others while preserving everyone's privacy. In this work, we propose that sharing the approximated behavior metric-based state projection function is a promising way to enhance the performance of FRL and concurrently provides an effective protection of sensitive information. We introduce FedRAG, a FRL framework to learn a computationally practical projection function of states for each client and aggregating the parameters of projection functions at a central server. The FedRAG approach shares no sensitive task-specific information, yet provides information gain for each client. We conduct extensive experiments on the DeepMind Control Suite to demonstrate insightful results.
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。