DeepAI
Log In Sign Up

Strategic Features for General Games

01/04/2021
by   Cameron Browne, et al.
0

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.

READ FULL TEXT
12/30/2020

Modern Techniques for Ancient Games

Games potentially provide a wealth of knowledge about our shared cultura...
10/01/2019

Mistakes in Games

We define a new concept of "mistake" strategies and actions for strategi...
01/23/2021

Deep Learning for General Game Playing with Ludii and Polygames

Combinations of Monte-Carlo tree search and Deep Neural Networks, traine...
01/18/2019

Decomposition of games: some strategic considerations

Candogan et al. (2011) provide an orthogonal direct-sum decomposition of...
04/23/2020

Games in Minkowski Spacetime

This paper contributes a new class of games called spacetime games with ...
06/29/2019

Ludii as a Competition Platform

Ludii is a general game system being developed as part of the ERC-funded...
06/08/2016

Simplified Boardgames

We formalize Simplified Boardgames language, which describes a subclass ...