Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower

arXiv:2611.11998 · cs.LG · Submitted 2026-11-09 · Read on arXiv

cs.LG

Submitted: 2026-11-09

Updated: 2026-11-09

Code: https://github.com/akimotolab/RE-HG

Terminology

Related papers