Action-depedent Control Variates for Policy Optimization via Stein's Identity

57 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.

Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods (2019, background): “In practice, it has been observed that these CVs indeed accelerate policy optimization, especially in simulated robot control tasks [20, 21, 23, 25, 36].”
P3O: Policy-on Policy-off Policy Optimization (2019, background): “Let us note that more general state-action dependent baselines can also be used (Liu et al., 2017).”
A survey and critique of multiagent deep reinforcement learning (2018, background): “e, Q(s;a;) can be used to approximate the state-action values with representing the neural network weights. This has two advantages,rst, deep learning 3Action-dependant baselines had been proposed [57, 58], however, a recent study by Tucker et al. [59] found that in many works the reason of good per”
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (2021, background): “[63] show that high performances of actiondependent baselines [19, 17, 37, 20, 67] were more directly due to different subtle implementation choices.”
Neural Approaches to Conversational AI (2018, unknown): “ years, attracting signiﬁcant attention from the QA research community. 29 Figure 3.8: Two examples of state of the art neural MRC models. (Left) The Stochastic Answer Net (SAN) model. Figure credit: Liu et al. (2018d). (Right) The BiDirectional Attention Flow (BiDAF) model. Figure credit: Seo et al”