Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Game-Guided Skill Discovery through Self-Play for Playable Agent Control
Seungeun Rho, Jeonghwan Kim, Xue Bin Peng +1
We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a com…
cs.LG2025
Reference Grounded Skill Discovery
Seungeun Rho, Aaron Trinh, Danfei Xu +1
Scaling unsupervised skill discovery algorithms to high-DoF agents remains challenging. As dimensionality increases, the exploration space grows exponentially, while the manifold o…