Some of the other combinations of the dimensions include the following. Hierarchical planning is discussed by Nau [2007]. Hierarchical reinforcement learning is covered by Dietterich [2000b]. Multiagent reinforcement learning is addressed by Stone [2007]. Inverse reinforcement learning is introduced by Ng and Russell [2000] and discussed by Russell [2019]. Dzeroski et al. [2001] overview relational reinforcement learning. Khardon and Sanner [2021] discuss relational decision-theoretic planning.

Challenges for the future of AI are described by Russell [2019], Marcus and Davis [2019], Littman et al. [2021] and Brachman and Levesque [2022a].