Skip to main content
Search

# Hierarchical Credit Assignment

2 related articles

Subscribe to updates
  1. arXiv

    Joint text-to-video post-training stops sharing one reward: prompt and generator get separate credit, lifting a matched LTX-2.5 control from 61.47 to 64.46

    FlowCred splits the single terminal reward of joint text-to-video post-training into prompt-level credit and prompt-conditioned generator residuals, lifting a strictly matched joint-training control on LTX-2.5 from 61.47 to 64.46 on T2V-CompBench without increasing decoded-video or reward-model-call budgets.

    Hong Kong University of Science and TechnologyShanghai Jiao Tong UniversityUniversity of Hong KongSouth China University of Technology
    Mingxuan Zhu（First author）
    FlowCredHierarchical Credit AssignmentFunctional CoordinationText-to-Video GenerationFlow-GRPO
  2. arXiv

    AlignOPSD aligns long-horizon agent supervision to functional decisions rather than timestamps, beating GRPO by 5.5–8.7% on ALFWorld, WebShop, and Search-QA

    The work identifies Decision–Timestamp Mismatch in on-policy self-distillation for long-horizon agents—privileged guidance may correspond to a decision at a different timestep, and a student decision may span multiple timesteps—and introduces AlignOPSD, which first rectifies privileged supervision using functional correspondences across sibling rollouts and then applies semi-Markov hierarchical credit assignment over variable-duration decision spans; with Qwen2.5-3B/7B it outperforms GRPO on all eight backbone–aggregate-metric comparisons across ALFWorld, WebShop, and Search-QA by 5.5–8.7%, ranking first in six.

    Beihang UniversityTsinghua University
    Mingju Chen（First author）
    AlignOPSDOn-Policy Self-DistillationHierarchical Credit AssignmentLLM AgentsAgentic Reinforcement Learning

You’re all caught up