A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
This is an incremental review paper that synthesizes existing methods for researchers in sequential decision making.
This review paper examines symbolic, subsymbolic, and hybrid methods for sequential decision making, comparing automated planning and reinforcement learning approaches and concluding that neurosymbolic AI shows promise for combining their strengths.
In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this article reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.