Multi-Agent Systems of Inverse Reinforcement Learners in Complex Games

Reinforcement Learning (RL) allows an agent to discover a suitable policy to achieve a goal. However, interesting problems for RL become complex extremely fast, as a function of the number of features that compose the state space. The proposed research is to decompose a core problem into tasks with only the features required to solve the task. The core agent then uses the reward for the task, without knowing the underlying task model. This paper discusses task-based RL and Inverse Reinforcement Learning to train the tasks.