Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibit much finer control over their planning process than traditional methods. We empirically demonstrate that this increased flexibility allows for more efficient planning by showing that an implementation of prioritized sweeping based on small backups achieves a substantial performance improvement over classical implementations.
[1]
Chris Watkins,et al.
Learning from delayed rewards
,
1989
.
[2]
Longxin Lin.
Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching
,
2004,
Machine Learning.
[3]
Richard S. Sutton,et al.
Reinforcement Learning: An Introduction
,
1998,
IEEE Trans. Neural Networks.
[4]
J. Peng,et al.
Efficient Learning and Planning Within the Dyna Framework
,
1993,
IEEE International Conference on Neural Networks.
[5]
Andrew W. Moore,et al.
Prioritized Sweeping: Reinforcement Learning with Less Data and Less Time
,
1993,
Machine Learning.
[6]
Richard S. Sutton,et al.
Learning to predict by the methods of temporal differences
,
1988,
Machine Learning.
[7]
C. Atkeson,et al.
Prioritized Sweeping: Reinforcement Learning with Less Data and Less Time
,
1993,
Machine Learning.
[8]
Andrew W. Moore,et al.
Reinforcement Learning: A Survey
,
1996,
J. Artif. Intell. Res..