Player-Centric Procedural Content Generation: Enhancing Runtime Customization by Integrating...
summary
A runtime PCG system called Player-Centric PCG presents levels generated from a manipulable feature vector, solicits one-line feedback after each run, and learns via a rejection-based sampler that labels disliked regions as deadzones so they are not reselected. Implemented in a Pac‑Man domain, it achieves high recall on static preferences but lower precision, and tests across short-term, medium, long and infinite memory show short-term best recovers after jump changes while long-term better handles gradual shifts.
AI-written summary · about
related talks
57mProcedural Generation: Fun = Feasability + Fairness + Interestingness
43mA Progressive-Adaptive Music Generator (PAMG): An Approach to Interactive Procedural(…)
38mProcedural Generation at Runtime: From Basic to Complex by Example
05mArtificial Players in the Design Process: Developing an automated testing tool for game level ...
03mInvestigating the Implementation and Effects of Personalized Gamification in Education
45mPanel: Can Generative AI be infused in Gaming?
06mGAME: Game As a Measurement Environment - Scheme to Evaluate Interfaces and Game Contents Based ...
06mUnderstanding Player Patterns by Combining Knowledge-Based Data Abstraction with Interactive ...