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(λ) is applied to tram 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 pay load 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--Zwehen'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.
[1]
Dean Pomerleau,et al.
Efficient Training of Artificial Neural Networks for Autonomous Navigation
,
1991,
Neural Computation.
[2]
D. Pomerleau.
Eecient T Raining of Artiicial Neural Networks for Autonomous Navigation
,
1991
.
[3]
Gerald Tesauro,et al.
Practical Issues in Temporal Difference Learning
,
1992,
Mach. Learn..
[4]
Steven J. Bradtke,et al.
Reinforcement Learning Applied to Linear Quadratic Regulation
,
1992,
NIPS.
[5]
Monte Zweben,et al.
Scheduling and rescheduling with iterative repair
,
1993,
IEEE Trans. Syst. Man Cybern..
[6]
Andrew W. Moore,et al.
Generalization in Reinforcement Learning: Safely Approximating the Value Function
,
1994,
NIPS.