Generalized TD Learning

30 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning (2019, methodology): “Luckett et al. (2018); Ueno et al. (2011) considered related semiparametric estimation techniques for the v -function.”
Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize (2015, background): “The recent work [49] considers an even broader class of Bellman equations using the concept”
Efficiently Breaking the Curse of Horizon: Double Reinforcement Learning in Infinite-Horizon Processes (2019, background): “Luckett et al. (2018); Ueno et al. (2011) considered related semiparametric estimation techniques for the v -function.”
Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning (2020, methodology): “Note that the regressions can also be replaced with Z-estimation (Ueno et al., 2011) based on the moment equations: E[gt(st, at) {rt + qt+1(st+1, π)− qt(st, at)}] = 0, ∀gt, t ≤ H.”