epo-entropy-regularized-policy-optimization

【效率与协作】Stabilize multi-turn LLM agent training with entropy-regularized policy optimization that prevents exploration-exploitation cascade failures in sparse-reward environments through trajectory-level entropy regulation, historical smoothing, and adaptive phase-based weighting. Achieve up to 152% performance improvement on scientific reasoning tasks and 1…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准