Konami (Japan)

The difficulty in exploring the game balance has been increasing, especially in Game-as-a-Service (GaaS) with updates in every few weeks, and due to the complexity in game design and business models. In the limited time available for testing, using automated game agents enables much more test plays than using human test players does, and it has been accelerated by the recent progress of deep reinforcement learning. However, understanding specific behaviours of each agent is hard due to their “black-box” nature. In this paper, we propose a method for explaining the behaviour of game agents using differential comparison between agents. This comparison approach is motivated by our experience with existing explanation techniques that often extracted uninteresting, common aspects of the behaviour. In addition, there are large potentials for the application of the comparison: between agents with different learning algorithms, between human agents and automated agents, and between test agents and users. We applied our technique to a prototype of a commercial GaaS and confirmed our technique can extract specific differences between agents.

The architectural distortion is a very important finding in interpreting breast cancers as well as microcalcification and mass on mammograms. In despite of the importance for detecting architectural distortions, no algorithms for detecting them have been reported. The purpose of this study is to develop a new detection method for focal retraction that is one of architectural distortions around skinline. In order to extract the thick mammary gland regions, binarization technique is performed. The top-hat processing based on morphological operators is applied to determine the suspect depressed regions around skinline. The false positives are eliminated by the features of their sizes and positions. After applying this technique to 51 digitized mammograms, the detection sensitivity was 92% with 3.8 false positives per image. It is concluded that this technique is effective to detect the architectural distortion.

This paper deals with the problem of production scheduling in a two-stage hybrid flow shop, which consists of one machine in the first stage, and multiple process lines in the second stage. In the first stage, materials are batch-processed, which are then fed into one of several process lines in the second stage, depending on the final product specifications. First, we formulated the total flow time or makespan, the capacity utilization and the maximum work-in-process level as measures of manufacturing performance. We analysed, through a series of numerical experiments, how these performance measures are affected by lot sizing, sequencing rules and the scheduling scenario. The following points were clarified. (1) The ratio rule yields the best performance with regard to the makespan, but the LPT rule yields the best performance with regard to the maximum work-in-process level, (2) The optimum lot size is also affected by such operation conditions as the unit processing time, the setup time, and the ratio ...

To achieve an ideal colorimetric calibration for CMYK (cyan, magenta, yellow, and black) printers, we propose a novel CMYK determination technique under the restrictions of a colorimetric match, use of the entire color gamut, and a smooth gradation of each primary color. The algorithm proposed here includes the following steps: (1) obtain the two extreme conditions for CMYK combinations to be able to utilize the entire CMYK gamut, namely maximum black technique and minimum black technique; (2) determine an initial black amount that lies between the two conditions; (3) apply a smoothing technique for the black amount; and (4) determine the remaining colors, CMY, for colorimetric match. An iterative smoothing technique in a uniform color space is introduced to obtain visually "smoothed" black gradations. The gradation quallty for each primary color is evaluated with a hypothetical unstable printer. The smoothed CMYK technique eliminates sudden changes for each primary color, so that a printer using this technique becomes robust against a change of characteristic curves of the printer such as dot gain. Also, it is found that a CMYK combination using the technique is suitable for a lookup table and interpolation technique in practical conversions.

In order to achieve an ideal colorimetric calibration for CMYK (Cyan, Magenta, Yellow, and Black) printers, we propose a novel CMYK determination technique under the restrictions of a colorimetric match, use of the entire color gamut and a smooth gradation of each primary color. The algorithm proposed here includes the following steps: (1) Obtain the two extreme conditions for CMYK combinations to be able to utilize the entire CMYK gamut, namely Maximum Black technique and Minimum Black, (2) Determine an arbitrary black amount between the two conditions, (3) Apply a smoothing technique for the black amount in a uniform color space, (4) Determine the remaining colors, CMY, for colorimetric match. An iterative smoothing technique in a uniform color space is introduced to obtain visually black gradations. The gradation quality for each primary color is evaluated with a hypothetical unstable printer. The smoothed CMYK technique eliminates sudden changes for each primary color, so that a printer using this technique becomes robust against a change of characteristic curves of the printer such as dot gain.

A timesaving simplified calculation method by means of the 3rdorder spherical aberration coefficient has been developed to evaluate the root mean square (RMS) wavefront error change of a moisture absorbed aspherical plastic singlet for an optical disk. 1.

A precise, multi-purpose color reproduction algorithm is introduced. This algorithm adopts 3-dimensional interpolation instead of matrix maskings or formulas. To install this calculation algorithm in devices, a simplified circuit using several LUT(ROM/RAM) and one multiplier/accumulator was developed. It can be operated up to 2 MHz pixel frequencies and its calculation error is estimated to be less than one-tenth of conventional method.