[Computer-go] PhD thesis (Lukasz Lew)
lukasz.lew at gmail.com
Sun Nov 13 14:27:11 PST 2011
Here's my phd thesis (not defended yet):
Most interesting stuff:
Section 4.7.6: Simple online variant of Minorization-Maximization with
small memory requirements.
Section 5.0: Why divide-and-conquer (or equivalently:
adaptive-playouts) are important.
Section 5.2: Why simple pattern-based adaptive playout can't work well.
Section 5.3, 5.4: Why linear model adaptive playout (for instance
TD(lambda), Dyna-2) can't work well.
Section 5.5, 5.6: Hopefully simple explanation of basic Combinatorial
Game Theory and Thermographs.
Section 5.8 Monte-Carlo-like algorithm applied to CGT (with simplified
thermographs) converges to correct solution on a toy problem (contrary
to both previous algorithms).
More information about the Computer-go