1. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning;Sutton;Artificial Intelligence,1999
2. Q-cut - dynamic discovery of sub-goals in reinforcement learning;Menache,2002
3. Learning options in reinforcement learning;Stolle,2002
4. Using relative novelty to identify useful temporal abstractions in reinforcement learning;Simsek,2004
5. Identifying useful subgoals in reinforcement learning by local graph partitioning;Şimşek,2005