KnightCap: A chess program that learns by combining TD(lambda) with game-tree search
By Jonathan Baxter, Andrew Tridgell, Lex Weaver. 1999
In this paper we present TDLeaf(lambda), a variation on the TD(lambda) algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our chess program ``KnightCap'' used TDLeaf(lambda) to learn its evaluation function while playing on the Free Internet Chess Server (FICS, fics.onenet.net). The main success we report is that KnightCap improved from a 1650 rating to a 2150 rating in just 308 games and 3 days of play. As a reference, a rating of 1650 corresponds to about level B human play (on a scale from E (1000) to A (1800)), while 2150 is human master level. We discuss some of the reasons for this success, principle among them being the use of on-line, rather than self-play.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Sergey Levine
- Yoshua Bengio
- Yuxi Li
- Pieter Abbeel
- Ruslan Salakhutdinov
- Jakob N. Foerster
- Trevor Darrell
- Abhinav Kumar Gupta
Citations in the corpus
- The Hanabi Challenge: A New Frontier for AI Research (2019, methodology): “05587 [65] J.”
- Bootstrapping from Game Tree Search (2009, methodology): “Our experiences using TD-Leaf in this setting were similar to those described in (Baxter et al., 1998); within the limits of our training scheme, learning occurred, but only to the level of weak amateur play.”
- Neural Networks and Deep Learning (2018, unknown): “Some TD-learning methods for chess, such as NeuroChess [496], KnightCap [22], and Giraffe [259] have been explored, but were not as successful as conventional engines.”