Affiliation:
1. Department of Computer Science and AI, Universidad de Granada, Granada, Spain
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.
Publisher
Association for Computing Machinery (ACM)
Reference175 articles.
1. Learning first-order markov models for control;Abbeel Pieter;NeurIPS,2004
2. Neurosymbolic reinforcement learning and planning: A survey;Acharya Kamal;IEEE Trans. Artif. Intell.,2023
3. Goal Reasoning: Foundations, Emerging Applications, and Prospects
4. A review of learning planning action models
5. A survey of inverse reinforcement learning: Challenges, methods and progress