Analysis of Evaluation-Function Learning by Comparison of Sibling Nodes

By Tomoyuki Kaneko, Kunihito Hoki. 2011

6 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Sergey Levine
2. Pieter Abbeel
3. Yuxi Li
4. Yoshua Bengio
5. Timothy P. Lillicrap
6. David Silver
7. Chelsea Finn
8. Ruslan Salakhutdinov

In Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. Timothy P. Lillicrap
4. Yuxi Li
5. David Silver
6. Jimmy Ba
7. Shimon Whiteson
8. R´emi Munos

Citations in the corpus

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017, background): “Kaneko and Hoki (17) trained the weights of a shogi evaluation function comprising a million features, by learning to select expert human moves during alpha-beta serach.”
• Large-Scale Optimization for Evaluation Functions with Minimax Search (2014, methodology): “Note that we have found that the errors caused by this approximation are sufficiently small for the shogi application (Kaneko & Hoki, 2012).”