A basic formula for online policy gradient algorithms

By Xi-Ren Cao. 2005

40 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

1. Pratik Chaudhari
2. Alex Smola
3. Rasool Fakoor
4. Sergey Levine
5. Yoshua Bengio
6. Pieter Abbeel
7. Bernhard Schölkopf
8. Quoc V. Le

In Computational Theory and Mathematics

1. Pratik Chaudhari
2. Pieter Abbeel
3. Jie Tang
4. Rasool Fakoor
5. Alex Smola
6. Sergey Levine
7. Jan Peters
8. Mikhail Belkin

In Control and Systems Engineering

1. Pratik Chaudhari
2. Rasool Fakoor
3. Pieter Abbeel
4. Jie Tang
5. Alex Smola
6. Sergey Levine
7. Chelsea Finn
8. Vikash Kumar

Citations in the corpus

• P3O: Policy-on Policy-off Policy Optimization (2019, methodology): “The importance sampling ratio has been commonly used by a number of authors such Cao (2005); Levine and Koltun (2013).”
• On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient (2010, background): “Cao [17] also uses importance sampling to reuse past data for estimating policy gradients, but focuses on estimating local gradient information rather than global surface information.”