Ready player one

Ready player one

Problem being addressed

The world of competitive Esports and video gaming has seen and continues to experience steady growth in popularity and complexity​,​ which provides vast opportunities for machine learning to develop accurate training algorithms​,​ detect addictive behavior and minimize risks.

Solution

Intelligent agent recommendation engine that suggests actions to players in order to maximise success and enjoyment, both in the space of in-game choices, as well as decisions made around play session timing in the broader context. The suggested model uses various methods to accommodate participant’s immediate historical performances within a win prediction model.

Advantages of this solution

The suggested model achieves a state-of-the-art accuracy an improvement over previous work based on strategic player behaviour. It’s able to learn atypical, subtle and complex nonlinearities corresponding to short-term fluctuations in momentum from a large, comprehensive dataset of player histories.

Possible New Application of the Work

/static/media/finance.6c751434.png

Financial Sector

The suggested model can be successfully applied in high performance environments such as financial trading to minimize financial risk and optimize strategic planning.

/static/media/sports.6db914a9.png

Sports Industry

The model can also be used for training in traditional team sports to develop the team strategy, analyze the players’ behavior during long play sessions and their reactions to their own failures.

/static/media/others.cca5db97.png

Other Industry

Security: Emergency departments, as well as certain military divisions, need to be trained to act in various conditions, and the suggested algorithm can create different possible combinations of interactions between humans to make each training scenario, though performed in an identical setting, unique in nature and line. This creates a diverse set of learning scenarios in the zone of proximal development.

Author of original research described in this blitzcard: Alfonso White, Daniela M. Romano

question-mark-icon

Name of the author who conducted the original research that this blitzcard is based on.

Source URL: #############check-icon


search-iconBrowse all blitzcards