Incremental dynamic programing may yield nonoptimal solutions

It is shown in this paper, with two examples, that incremental dynamic programing may converge to a nonoptimal solution if the same state increment is used for every stage. Then it is shown how to adjust the increment sizes in each stage to obtain the desired results.

[1]  B. Bernholtz,et al.  Hydrothermal Economic Scheduling Part 1. Solution by Incremental Dynamic Programing , 1960, Transactions of the American Institute of Electrical Engineers. Part III: Power Apparatus and Systems.

[2]  V. T. Chow,et al.  Discrete Differential Dynamic Programing Approach to Water Resources Systems Optimization , 1971 .

[3]  V. T. Chow,et al.  Application of DDDP in water resources planning , 1974 .