Hyunseok Kim

Coverage-Aware Guidance for Novelty-Driven Exploration in Automated Game Testing Under Sparse-Reward 3-D Environments

Automated testing of high-fidelity 3D games requires agents to explore large state spaces under sparse rewards and execute context-dependent interactions that expose faults. Random network distillation (RND) promotes exploration by rewarding observations that remain difficult for a predictor network to estimate, but pr...