Computer

The results showed that agents that implement a dynamic game balancingapproach performed close to user level, and also provided the highest user satisfaction, validating our hypothesis of mutual influence between game balance and user satisfaction.

adaptive approaches are more effective

This work presents an evaluation, performed by human players, of dynamic game balancing approaches

This release simplifies several aspects of the game as it is played by humans

This paper introduces StarCraft II as a new challenge for deep reinforcement learning research

This paper introducesSC2LE(StarCraft II Learning Environment), a reinforce-ment learning environment based on the game StarCraft II

We describe the observation, action, and rewardspecification for the StarCraft II domain and provide an open source Python-basedinterface for communicating with the game engine.

We describe the observation, action, and rewardspecification for the StarCraft II domain

a recognized major concern for the game developers’ community is to provide mechanisms to dynamically balance the difficulty level of the games in order to keep the user interested in playing