kage-bench-fast-known-axis-visual-generalization

【设计与创意】Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis. We introduce KAGE-Env, a JAX-native 2D platformer that factorizes the observation process into independently control…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准