FedQHD: Closed-Form Function-Space Federated Reinforcement Learning

arXiv:2605.29002v1 Announce Type: new Abstract: 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. We propose FedQHD, a fe