action-quantization-behavior-cloning

【设计与创意】Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose model-based augmentation to reduce error dependence from H² to H.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准