Option Discovery in Reinforcement Learning using Frequent Common Subsequences of Actions

Temporally abstract actions, or options, facilitate learning in large and complex domains by exploiting sub-tasks and hierarchical structure of the problem formed by these sub-tasks. In this paper, we study automatic generation of options using common sub-sequences derived from the state transition histories collected as learning progresses. The standard Q-learning algorithm is extended to use generated options transparently, and effectiveness of the method is demonstrated in Dietterich´s Taxi domain