Experiments in Parameter Learning Using Temporal Differences

By Jonathan Baxter, Andrew Tridgell, Lex Weaver. 1998

How researchers see this paper

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

1. David Silver
2. Yuxi Li
3. Richard S. Sutton
4. Sergey Levine
5. Csaba Szepesvari
6. Hado van Hasselt
7. R´emi Munos
8. Yoshua Bengio

Citations in the corpus

• Combining online and offline knowledge in UCT (2007, methodology): “, 2007), and which has proven successful in many other domains (Baxter et al., 1998; Schaeffer et al., 2001; Buro, 1999).”
• A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation (2008, methodology): “Linear methods, on the other hand, have been widely used (e.g., Baxter, Tridgell & Weaver 1998; Sturtevant & White 2006; Schaeffer, Hlynka & Jussila 2001).”
• Reinforcement Learning of Local Shape in the Game of Go (2007, result): “A similar approach attained master level play in Chess [1].”
• Sample-based learning and search with permanent and transient memories (2008, methodology): “The heuristic is typically approximated by a linear combination of binary features, and can be learned offline by temporaldifference learning and self-play (Baxter et al., 1998; Schaeffer et al., 2001; Buro, 1999).”