dcpo-dynamic-clipping-policy-optimization

【效率与协作】DCPO eliminates zero-gradient dead zones in policy optimization by adaptively adjusting token-level clipping bounds based on prior probabilities and smoothing advantage standardization across cumulative training steps, achieving 28% improvement in effective response utilization and 10x reduction in token clipping ratio on mathematical reasoning bench…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准