Inverse Reinforcement Learning for Strategy Identification
This work addresses strategy identification for adversarial scenarios like combat games, but it is incremental as it applies an existing method (IRL) to a new domain.
The paper tackles the problem of identifying an opponent's strategy in adversarial environments by using inverse reinforcement learning (IRL) to estimate strategies from observed actions, with results demonstrated on gaming combat data generated from three pre-defined strategies.
In adversarial environments, one side could gain an advantage by identifying the opponent's strategy. For example, in combat games, if an opponents strategy is identified as overly aggressive, one could lay a trap that exploits the opponent's aggressive nature. However, an opponent's strategy is not always apparent and may need to be estimated from observations of their actions. This paper proposes to use inverse reinforcement learning (IRL) to identify strategies in adversarial environments. Specifically, the contributions of this work are 1) the demonstration of this concept on gaming combat data generated from three pre-defined strategies and 2) the framework for using IRL to achieve strategy identification. The numerical experiments demonstrate that the recovered rewards can be identified using a variety of techniques. In this paper, the recovered reward are visually displayed, clustered using unsupervised learning, and classified using a supervised learner.