Elastic Monte Carlo Tree Search with State Abstraction for Strategy Game Playing

05/30/2022
by   Linjie Xu, et al.
0

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 abstraction methods for games depend on domain knowledge, making their application to new games expensive. State abstraction methods that require no domain knowledge are studied extensively in the planning domain. However, no evidence shows they scale well with the complexity of strategy games. In this paper, we propose Elastic MCTS, an algorithm that uses state abstraction to play strategy games. In Elastic MCTS, the nodes of the tree are clustered dynamically, first grouped together progressively by state abstraction, and then separated when an iteration threshold is reached. The elastic changes benefit from efficient searching brought by state abstraction but avoid the negative influence of using state abstraction for the whole search. To evaluate our method, we make use of the general strategy games platform Stratega to generate scenarios of varying complexity. Results show that Elastic MCTS outperforms MCTS baselines with a large margin, while reducing the tree size by a factor of 10. Code can be found at: https://github.com/egg-west/Stratega

READ FULL TEXT

page 1

page 3

research
04/17/2021

Generating Diverse and Competitive Play-Styles for Strategy Games

Designing agents that are able to achieve different play-styles while ma...
research
04/24/2017

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

Monte Carlo Tree Search techniques have generally dominated General Vide...
research
01/23/2021

Deep Learning for General Game Playing with Ludii and Polygames

Combinations of Monte-Carlo tree search and Deep Neural Networks, traine...
research
11/07/2022

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

The success of AlphaZero (AZ) has demonstrated that neural-network-based...
research
03/08/2021

Monte Carlo Tree Search: A Review of Recent Modifications and Applications

Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-...
research
08/04/2019

Monte-Carlo Tree Search for Simulation-based Strategy Analysis

Games are often designed to shape player behavior in a desired way; howe...
research
01/18/2014

Learning to Win by Reading Manuals in a Monte-Carlo Framework

Domain knowledge is crucial for effective performance in autonomous cont...

Please sign up or login with your details

Forgot password? Click here to reset