A Unifying Framework for Reinforcement Learning and Planning

A Unifying Framework for Reinforcement Learning and Planning

Moerland, Thomas M. (Universiteit Leiden)
Broekens, D.J. (Universiteit Leiden)
Plaat, Aske (Universiteit Leiden)
Jonker, C.M. (TU Delft Interactive Intelligence; Universiteit Leiden)

2022

Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both largely have their own research communities. However, if both research fields solve the same problem, then we might be able to disentangle the common factors in their solution approaches. Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning and learning algorithms have to decide. At the end of the paper, we compare a variety of well-known planning, model-free and model-based RL algorithms along these dimensions. Altogether, the framework may help provide deeper insight in the algorithmic design space of planning and reinforcement learning.

framework
model-based reinforcement learning
overview
planning
reinforcement learning
synthesis

http://resolver.tudelft.nl/uuid:e29c644e-4bf7-48a5-8b8d-f1e8ec7afe91

https://doi.org/10.3389/frai.2022.908353

2624-8212

Frontiers in Artificial Intelligence, 5

Institutional Repository

journal article

© 2022 Thomas M. Moerland, D.J. Broekens, Aske Plaat, C.M. Jonker