Biasing MCTS with Features for General Games
This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and hardware) required for training. Features describing local patterns are used as inputs. The features are formulated in such a way that they are easily interpretable and applicable to a wide range of general games, and might encode simple local strategies. We gradually create new features during the same self-play training process used to learn feature weights. We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly improved playing strength in the majority of them after a small number of self-play training games.
Code (1)
Tasks
Board GamesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Strategic Features for General Games
This short paper describes an ongoing research project that requires the automated self-play learning and evaluation of a large number of board games in digital form. We describe the approach we are taking to determine r…
Board GamesConvergence of Monte Carlo Tree Search in Simultaneous Move Games
In this paper, we study Monte Carlo tree search (MCTS) in zero-sum extensive-form games with perfect information and simultaneous moves. We present a general template of MCTS algorithms for these games, which can be inst…
FormHybrid Minimax-MCTS and Difficulty Adjustment for General Game Playing
Board games are a great source of entertainment for all ages, as they create a competitive and engaging environment, as well as stimulating learning and strategic thinking. It is common for digital versions of board game…
Board GamesUnlucky Explorer: A Complete non-Overlapping Map Exploration
Nowadays, the field of Artificial Intelligence in Computer Games (AI in Games) is going to be more alluring since computer games challenge many aspects of AI with a wide range of problems, particularly general problems. …
Elastic Monte Carlo Tree Search with State Abstraction for Strategy Game Playing
Strategy video games challenge AI agents with their combinatorial search space caused by complex game elements. State abstraction is a popular technique that reduces the state space complexity. However, current state abs…