A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
arXiv:2304.10590 · doi:10.1145/3663366
Abstract
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.
35 pages, 16 figures
References in corpus (8)
- Language Models are Few-Shot Learners
- Interaction Networks for Learning about Objects, Relations and Physics
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- Learning model-based planning from scratch
- Neurosymbolic Reinforcement Learning and Planning: A Survey
- Learning to Select Goals in Automated Planning with Deep-Q Learning
- The Value Equivalence Principle for Model-Based Reinforcement Learning
- Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey