Abstract
The Monte Carlo Tree Search in the game of Go tends to produce unstable and unreasonable results when used in situations of extreme advantage or disadvantage, due to poor move selection because of low signal-to-noise ratio; notably, this occurs when playing in high handicap games, burdening the computer with further disadvantage against the strong human opponent. We explore and compare multiple approaches to mitigate this problem by artificially evening out the game based on modi- fication of the final game score by variable amount of points ("dynamic komi") before storing the result in the game tree.
We also compare performance of MCTS and traditional tree search in the context of extreme situations and measure the effect of dynamic komi on actual playing strength of a state-of-art MCTS Go program. Based on our results, we also conjencture on resilience of the game search tree to changes in the evaluation function throughout the search.