A reinforcement learning approach to job-shop scheduling (1995) [80 citations — 7 self]

Download:

by Wei Zhang, Thomas G. Dietterich

In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence

http://www.cs.orst.edu/~tgd/publications/ijcai95-jss.ps.gz

Add To MetaCart

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@INPROCEEDINGS{Zhang95areinforcement,
    author = {Wei Zhang and Thomas G. Dietterich},
    title = {A reinforcement learning approach to job-shop scheduling},
    booktitle = {In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence},
    year = {1995},
    pages = {1114--1120},
    publisher = {Morgan Kaufmann}
}

Years of Citing Articles

Abstract:

We apply reinforcement learning methods to learn domain-specific heuristics for job shop scheduling. A repair-based scheduler starts with a critical-path schedule and incrementally repairs constraint violations with the goal of finding a short conflict-free schedule. The temporal difference algorithm TD() is applied to train a neural network to learn a heuristic evaluation function over states. This evaluation function is used by a one-step lookahead search procedure to find good solutions to new scheduling problems. We evaluate this approach on synthetic problems and on problems from a NASA space shuttle payload processing task. The evaluation function is trained on problems involving a small number of jobs and then tested on larger problems. The TD scheduler performs better than the best known existing algorithm for this task---Zweben's iterative repair method based on simulated annealing. The results suggest that reinforcement learning can provide a new method for constructing high-performance scheduling systems.

Citations

885	Learning to Predict by the Methods of Temporal Differences – Sutton - 1988
287	Practical issues in temporal difference learning – Tesauro - 1992
170	Generalization in reinforcement learning: Safely approximating the value function – Boyan, Moore - 1995
92	Knowledge-Based Training of Artificial Neural Networks for Autonomous Robot Driving – Pomerleau - 1993
87	Scheduling and Rescheduling with Iterative Repairs – Zweben, Davis, et al. - 1994
48	Reinforcement learning applied to linear quadratic regulation – Bradtke
8	The space shuttle ground processing scheduling system – Deale, Yvanovich, et al. - 1994
2	Using TD() to learn an evaluation function for the game of Go – Schraudolph, Dayan, et al. - 1994
2	Issues in using approximation for reinforcement learning – Thrun, Schwartz - 1993
1	A Boyan and A W Moore Generalization in reinforcement learning safely approximating the value function – unknown authors - 1995
1	Reinforc ement learning applied to linear quadratic regulation – Bradtke - 1993
1	A Pomerleau Efficient training of artificial neural networks for autonomous navigation – unknown authors - 1991
1	P Dayan and T Sejnowski Using to learn an evalu ation function for the game of go – Schraudolph - 1994

View or Download | Add to My Collection | Correct Errors