OFUGLB outperforms or is at par with prior algorithms for logistic bandits.

Intelligent agents must be generalists, capable of quickly adapting to various tasks.

Code is at this URL.

Constrained decision-making problems are pervasive across various disciplines.

We further propose a federated natural actor critic (NAC) method for multi-task RL with function approximation and stochastic policy evaluation, and establish its finite-time sample complexity taking the errors of function approximation into account.