Combining Neural Networks for Controlling Non-player Characters in Games

Sagredo-Olivenza, Ismael; Gómez-Martín, Pedro Pablo; Gómez-Martín, Marco Antonio; González-Calero, Pedro A.

doi:10.1007/978-3-319-59147-6_59

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Papers Reinforcement [40], [51], [81], [6], [179], [176], [67], [66], [128], [51], [180], [183] Evolutionary [65], [94], [129], [45], [118], [177], [109], [173], [44], [11], [108], [146], [77], [106], [107], [77], [76], [32], [146], [106], [174], [61] Case Based Reasoning [46], [119], [48], [180] From Demonstration [50], [143], [17] policy representation for both learning and planning approaches, with the hope of improving both performance and design time.…”

Section: Learning Methodsmentioning

confidence: 99%

“…Learning by demonstration has shown improvements in generating more human-like behavior, although in situations where human behavior was less predictable, the resulting NPC behaviors might not meet expectations [17]. Machine learning functions, such as neural networks, have been used in combination with BTs to let game developers combine hand-coded BTs with programming by demonstration [143]. This technique can increase performance in uncertain environments thanks to the noise tolerance of neural networks.…”

Section: Learning From Demonstrationmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Behavior Trees in Robotics and AI

Iovino¹,

Scukins²,

Styrud³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Section: Learning Methodsmentioning

confidence: 99%

Section: Learning From Demonstrationmentioning

confidence: 99%

A Survey of Behavior Trees in Robotics and AI

Iovino¹,

Scukins²,

Styrud³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…VPEs integrate a selected Visual Programming Language (VPL) to enable their users to create applications on the basis of such graphical elements as icons, blocks, arrows, forms, and figures, among others, rather than code only [25,26] . The relevance of these development tools has recently increased not only in Robotics-related use cases, but also in other fields of Computer Science such as the Internet of Things (IoT) [25,27] , video game development [28,29] , mobile application development [30] , and Virtual/Augmented Reality [31] . Due to their aforementioned flexibility and relevance, this article focuses on the EUD tools using VPEs for the design of Social Robotics applications.…”

Section: Introductionmentioning

confidence: 99%

Visual Programming Environments for End-User Development of intelligent and social robots, a systematic review

Coronado

Mastrogiovanni

Indurkhya

et al. 2020

Journal of Computer Languages

View full text Add to dashboard Cite

Robots are becoming interactive and robust enough to be adopted outside laboratories and in industrial scenarios as well as interacting with humans in social activities. However, the design of engaging robotbased applications requires the availability of usable, flexible and accessible development frameworks, which can be adopted and mastered by researchers and practitioners in social sciences and adult end users as a whole. This paper surveys Visual Programming Environments aimed at enabling a paradigm fostering the so-called End-User Development of applications involving robots with social capabilities. The focus of this article is on those Visual Programming Environments that are designed to support social research goals as well as to cater for professional needs of people not trained in more traditional text-based computer programming languages. This survey excludes interfaces aimed at supporting expert programmers, at allowing industrial robots to perform typical industrial tasks (such as pick and place operations), and at teaching children how to code. After having performed a systematic search, sixteen programming environments have been included in this survey. Our goal is two-fold: first, to present these software tools with their technical features and Authoring Artificial Intelligence modeling approaches, and second, to present open challenges in the development of Visual Programming Environments for end users and social researchers, which can be informative and valuable to the community. The results show that the most recent such tools are adopting distributed and Component-Based Software Engineering approaches and web technologies. However, few of them have been designed to enable the independence of end users from high-tech scribes. Moreover, findings indicate the need for (i) more objective and comparative evaluations, as well as usability and user experience studies with real end users; and (ii) validations of these tools for designing applications aimed at working "in-the-wild" rather than only in laboratories and structured settings.

show abstract