Machine Learning

, Volume 13, Issue 1, pp 103–130

Prioritized sweeping: Reinforcement learning with less data and less time

  • Andrew W. Moore
  • Christopher G. Atkeson

DOI: 10.1007/BF00993104

Cite this article as:
Moore, A.W. & Atkeson, C.G. Mach Learn (1993) 13: 103. doi:10.1007/BF00993104


We present a new algorithm,prioritized sweeping, for efficient prediction and control of stochastic Markov systems. Incremental learning methods such as temporal differencing and Q-learning have real-time performance. Classical methods are slower, but more accurate, because they make full use of the observations. Prioritized sweeping aims for the best of both worlds. It uses all previous experiences both to prioritize important dynamic programming sweeps and to guide the exploration of state-space. We compare prioritized sweeping with other reinforcement learning schemes for a number of different stochastic optimal control problems. It successfully solves large state-space real-time problems with which other methods have difficulty.

Key words

Memory-based learning learning control reinforcement learning temporal differencing asynchronous dynamic programming heuristic search prioritized sweeping 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 1993

Authors and Affiliations

  • Andrew W. Moore
    • 1
  • Christopher G. Atkeson
    • 1
  1. 1.MIT Artificial Intelligence Laboratory, NE43-771Cambridge

Personalised recommendations