In the classical decision-making literature, this is achieved by two interweaving processes, policyevaluation and policyimprovement (Sutton and Barto,2018).

Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards

We explore online learning in episodic Markov decision processes on non-stationary environments (changing losses and probability transitions).

Multi-task offline reinforcement learning aims to develop a unified policy for diverse tasks without requiring real-time interaction with the environment.

The capability of generating high-quality long-horizon trajectories makes it a promising research direction.

Reward specification is one of the most tricky problems in Reinforcement Learning, which usually requires tedious hand engineering in practice.

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.

Full experimental details are provided in Appendix C.