2020/06/30 by Thomas M. Moerland, Joost Broekens, Moerland, Thomas M. +5 · 83 citations
Computer Science · Decision Sciences · Mathematics · #Artificial Intelligence (cs.AI) #Artificial intelligence #Categorization #Complex Systems and Decision Making #Computer science #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Markov decision process #Markov process #Reinforcement Learning in Robotics #Reinforcement learning #Simulation Techniques and Applications #cs.AI #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2006.16712
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2020/06/30 · arxiv created 2022/03/31 · arxiv updated 2022/04/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a important challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This paper presents a survey of the integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover approaches to dynamics model learning, including challenges like dealing with stochasticity, uncertainty, partial observability, and temporal abstraction. Second, we present a systematic categorization of planning-learning integration, including aspects like: where to start planning, what budgets to allocate to planning and real data collection, how to plan, and how to integrate planning in the learning and acting loop. After these two sections, we also discuss implicit model-based RL as an end-to-end alternative for model learning and planning, and we cover the potential benefits of model-based RL. Along the way, the survey also draws connections to several related RL fields, like hierarchical RL and transfer learning. Altogether, the survey presents a broad conceptual overview of the combination of planning and learning for MDP optimization.