Monte Carlo Search Algorithms Discovering Monte Carlo Tree Search Exploration Terms
This work addresses an incremental improvement in optimizing exploration strategies for combinatorial search algorithms, potentially benefiting researchers and practitioners in AI and game playing.
The authors tackled the problem of designing exploration terms for Monte Carlo Tree Search algorithms by using Monte Carlo Search to automatically generate mathematical expressions for the PUCT and SHUSS algorithms, resulting in competitive performance with standard PUCT for small search budgets of 32 evaluations.
Monte Carlo Tree Search and Monte Carlo Search have good results for many combinatorial problems. In this paper we propose to use Monte Carlo Search to design mathematical expressions that are used as exploration terms for Monte Carlo Tree Search algorithms. The optimized Monte Carlo Tree Search algorithms are PUCT and SHUSS. We automatically design the PUCT and the SHUSS root exploration terms. For small search budgets of 32 evaluations the discovered root exploration terms make both algorithms competitive with usual PUCT.