safe-flow-q-learning

【效率与协作】Train offline safe RL agents using Hamilton-Jacobi reachability principles to learn feasibility-gated policies. Combine reward and safety critics with flow-matching teacher policies, distill to one-step actors, and calibrate safety thresholds via conformal prediction—achieving near-zero constraint violations with 2.5× inference speedup.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准