O2TD: (Near)-Optimal Off-Policy TD Learning

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions are optimal w.r.t approximating the true value function V . Two novel algorithms are proposed to approximate the true value function V . This paper makes the following contributions: • A batch algorithm that can help find the approximate optimal off-policy prediction of the true value function V . • A linear computational cost (per step) near-optimal algorithm that can learn from a collection of off-policy samples. • A new perspective of the emphatic temporal difference learning which bridges the gap between off-policy optimality and off-policy stability.