On the Convergence of Optimistic Policy Iteration

98 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.

Learning to Act by Predicting the Future (2016, background): “While the understanding of the convergence of both types of methods has since improved (Szepesv´ari & Littman, 1999; Tsitsiklis, 2002; Even-Dar & Mansour, 2003), the argument for TD versus Monte Carlo is to this day empirical (Sutton & Barto, 2017).”
Safe and Efficient Off-Policy Reinforcement Learning (2016, background): “The proof extends similar convergence proofs of TD( λ ) by Bertsekas and Tsitsiklis (1996) and of optimistic policy iteration by Tsitsiklis (2003), and is provided in the appendix.”
Temporal-difference search in computer Go (2012, unknown): “These problems can be described by a terminal reward of r = 1 for success, r = 0 for failure, and no intermediate rewards.”
Empirical Dynamic Programming (2013, background): “But the most closely related work is optimistic policy iteration [46] wherein simulated trajectories are used for policy evaluation while policy improvement is done exactly.”