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 relevant features, for biasing MCTS playouts for arbitrary games played on arbitrary geometries. Benefits of our approach include efficient implementation, the potential to transfer learnt knowledge to new contexts, and the potential to explain strategic knowledge embedded in features in human-comprehensible terms.
Code (0)
등록된 구현이 없습니다.
Tasks
Board GamesSimilar Papers 제목 키워드 기반
Learning Strategic Value and Cooperation in Multi-Player Stochastic Games through Side Payments
For general-sum, n-player, strategic games with transferable utility, the Harsanyi-Shapley value provides a computable method to both 1) quantify the strategic value of a player; and 2) make cooperation rational through …
FormQ-LearningMARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective…
Reinforcement LearningStrategic Teaching and Learning in Games
It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should players use such learning heuristics and where could they come from? We show that there is no uncoupled…
Strategic Reasoning with Language Models
Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do no…
Network Threshold Games
This paper studies the general class of games where agents: (1) are embedded on a network, (2) have two possible actions, and (3) these actions are strategic complements. We use a measure of network cohesiveness -- the k…