Fetching the paper…

Reading the bibliography…

Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm · Around

2021

Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm

Khodadadian, Sajad, Doan, Thinh T., Romberg, Justin et al.

Original
PDF
Post on X

Understand

Actor-critic style two-time-scale algorithms are one of the most popular methods in reinforcement learning, and have seen great empirical success.

However, their performance is not completely understood theoretically.
In this paper, we characterize the \emph{global} convergence of an online natural actor-critic algorithm in the tabular setting using a single trajectory of samples.
Our analysis applies to very general settings, as we only assume ergodicity of the underlying Markov decision process.

Built on

{barticle}
Original
1912
Earlier work this paper cites.
{barticle}
1951
Earlier work this paper cites.
{barticle}
1961
Earlier work this paper cites.
{barticle}
1990
Earlier work this paper cites.
{binproceedings}
1990
Earlier work this paper cites.
{barticle}
1992
Earlier work this paper cites.
{barticle}
1996
Earlier work this paper cites.
{barticle}
1999
Earlier work this paper cites.
{binproceedings}
2000
Earlier work this paper cites.
{binproceedings}
2002
Earlier work this paper cites.
{binproceedings}
2002
Earlier work this paper cites.

Similar

{barticle}
2008
Cited alongside, same era.
{binproceedings}
2010
Cited alongside, same era.
{binproceedings}
2010
Cited alongside, same era.
{binproceedings}
2012
Cited alongside, same era.
{barticle}
Original
2014
Cited alongside, same era.
{barticle}
2015
Cited alongside, same era.
{binproceedings}
2018
Cited alongside, same era.
{binproceedings}

Then

{barticle}
2019
Later among the works it cites.
{barticle}
2020
Later among the works it cites.
{barticle}
2020
Later among the works it cites.
{binproceedings}
2020
Later among the works it cites.
{barticle}
2020
Later among the works it cites.
{barticle}
2020
Later among the works it cites.
{barticle}
2021
Closest in time.
{barticle}
2021
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2018

Cited alongside, same era.

{barticle}

2019

Cited alongside, same era.

{barticle}

2019

Cited alongside, same era.

{barticle}

2019

Cited alongside, same era.

{barticle}

Cited in the paper.

2021

Closest in time.

{barticle}

2021

Closest in time.

2021

Closest in time.