From Reinforcement Learning to Optimal Control: A unified framework for sequential decisions
This work addresses the problem of disparate approaches in sequential decision-making for researchers and practitioners, but it is incremental as it builds on prior work to unify existing concepts.
The paper tackles the fragmentation in sequential decision-making fields by proposing a unified framework that covers 15 communities, highlighting parallels with stochastic optimal control and limitations of reinforcement learning's modeling framework.
There are over 15 distinct communities that work in the general area of sequential decisions and information, often referred to as decisions under uncertainty or stochastic optimization. We focus on two of the most important fields: stochastic optimal control, with its roots in deterministic optimal control, and reinforcement learning, with its roots in Markov decision processes. Building on prior work, we describe a unified framework that covers all 15 different communities, and note the strong parallels with the modeling framework of stochastic optimal control. By contrast, we make the case that the modeling framework of reinforcement learning, inherited from discrete Markov decision processes, is quite limited. Our framework (and that of stochastic control) is based on the core problem of optimizing over policies. We describe four classes of policies that we claim are universal, and show that each of these two fields have, in their own way, evolved to include examples of each of these four classes.