Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic

arXiv:2605.14423v1 Announce Type: cross Abstract: Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single shared policy across all agents. We consider a federated actor-critic framework in which agents share a common linear subspace representation while maintaining personalized local policy components, and agents itera