Direct Policy Search using Paired Statistical Tests

By Malcolm J. A. Strens, Andrew W. Moore. 2001

32 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.

1. Sergey Levine
2. Jens Kober
3. Jan Peters
4. Pieter Abbeel
5. J. Bagnell
6. Yoshua Bengio
7. Chelsea Finn
8. Abhinav Kumar Gupta

Citations in the corpus

• Reinforcement learning in robotics: A survey (2013, methodology): “The computation of the policy update is the key step here and a variety of updates have been proposed ranging from pairwise comparisons (Strens and Moore, 2001; Ng et al., 2004a) over gradient estimation using finite policy differences (Sato et al.”
• TTree: Tree-Based State Generalization with Temporally Abstract Actions (2002, background): “The individual trajectories are sampled with the randomness being controlled [12, 14].”
• Tree based hierarchical reinforcement learning (2002, background): “The individual trajectories are sampled with the randomness being controlled (Ng and Jordan, 2000; Strens and Moore, 2001).”