Policy Gradient Methods for Robot Control

By Jan Peters, Sethu Vijayakumar, Stefan Schaal. 2003

16 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

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

In Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. Chelsea Finn
4. Yan Duan
5. Abhishek Gupta
6. Xi Chen
7. Shixiang Shane Gu
8. John Schulman

Citations in the corpus

• Benchmarking Deep Reinforcement Learning for Continuous Control (2016, background): “Its final outcome is greatly affected by the performance of the initial policy, an observation that is consistent with the original work of Peters et al. (2010). This leads to a bad performance on average, although under particular initial settings the algorithm can perform on par with others.”
• Motor Learning at Intermediate Reynolds Number: Experiments with Policy Gradient on the Flapping Flight of a Rigid Wing (2010, background): “Techniques such as Natural Gradient (Amari, 1998; Peters et al., 2003) and GPOMDP (Baxter & Bartlett, 2001) have become popular through their ability to converge on locally optimal policies using fewer policy evaluations.”