Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI
This work addresses the need for more human-like AI in fighting games by enabling multidimensional difficulty, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of generating AI opponents in fighting games that exhibit multiple distinct strategies at each difficulty level, introducing a diversity-based deep reinforcement learning approach that outperforms a baseline with human-authored reward functions in both diversity and performance.
In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level" of difficulty. To make AI opponents more human-like, we'd ideally like to see multiple different strategies at each level of difficulty, a concept we refer to as "multidimensional" difficulty. In this paper, we introduce a diversity-based deep reinforcement learning approach for generating a set of agents of similar difficulty that utilize diverse strategies. We find this approach outperforms a baseline trained with specialized, human-authored reward functions in both diversity and performance.