AI RESEARCH
FedQHD: Closed-Form Function-Space Federated Reinforcement Learning
arXiv CS.LG
•
ArXi:2605.29002v1 Announce Type: new Federated reinforcement learning enables decentralized agents to collaboratively improve policies or value estimates without exchanging raw trajectories. However, FedAvg-style parameter averaging is not function-space consistent: when clients use heterogeneous encoders or even identical nonlinear networks, averaged parameters need not correspond to the weighted average of client value functions in any common function space.