Consequently, our framework transforms the task of proving convergence rate into verifying the positive semidefiniteness of a specific integral kernel.

Further, we are interested in algorithms that enjoy sample efficiency while leveraging (value) function approximation.

Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Traditional methods directly restrict the total return variance. Recent methods restrict the per-step reward variance as a proxy.

However, zero-shot learning methods still require human instruction set to solve a new task.