Directly Estimating the Variance of the λ-Return Using
Temporal-Difference Methods

v1v2 (latest)

Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods

25 January 2018

Brendan Bennett

Dylan R. Ashley

ArXiv (abs)PDF HTML

Papers citing "Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods"

6 / 6 papers shown

Title
Unifying task specification in reinforcement learning Martha White OffRL 57 90 0 07 Sep 2016
A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning Martha White Adam White 60 48 0 02 Jul 2016
On Convergence of Emphatic Temporal-Difference Learning Huizhen Yu OffRL 61 73 0 08 Jun 2015
Variance Adjusted Actor Critic Algorithms Aviv Tamar Shie Mannor OffRL 89 43 0 14 Oct 2013
ADADELTA: An Adaptive Learning Rate Method Matthew D. Zeiler ODL 163 6,632 0 22 Dec 2012
Policy Gradients with Variance Related Risk Criteria Dotan Di Castro Aviv Tamar Shie Mannor 101 210 0 27 Jun 2012