跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 6 天前AI 評分44

正則化分數中心化

Regularized Score Centering

AI 導讀

研究提出正則化分數中心化(RSC),透過加入反向 KL 懲罰,限制學習策略與生成數據的行為策略之間的差異,以穩定離策略學習。RSC 配合截斷重要性抽樣(TIS),在所有智能體基準測試中以相同數量的採樣回應取得更高訓練獎勵,並提升樣本效率。最終評測涵蓋的六項智能體任務均取得頂尖表現,在 AppWorld 提升 14.3%,在 BabyAI 的得分則達最強基線的 9.9 倍。

正文

Published on Nov 16

Authors:

,

,

,

Abstract

Asynchronous reinforcement learning increases training throughput, but data from stale policies and numerical mismatch between training and inference can destabilize learning. To stabilize off-policy learning, score centering (SC) removes the effect of reward baselines on the expected update. Our gradient diagnostics show less extreme gradients with SC than with importance sampling (IS), but SC can still fail when the learner moves far from the behavior policy that generated the data. To limit this policy mismatch, we introduce Regularized Score Centering (RSC), which adds a reverse Kullback-Leibler (KL) penalty to encourage the learner's next-token distribution to stay close to the behavior policy's next-token distribution. RSC works with or without truncated importance sampling (TIS), which caps token importance weights. Our theoretical analysis supports this approach, showing that KL regularization improves convergence guarantees. We evaluate dense and mixture-of-experts models on mathematical reasoning and agentic tasks, including online shopping, tool use, games, and fully asynchronous software engineering. RSC with TIS substantially improves sample efficiency across all agentic benchmarks, attaining higher training rewards with the same number of sampled responses. In final evaluations, it achieves top performance across all six agentic tasks, improving by 14.3% on AppWorld and reaching 9.9 times the strongest baseline's score on BabyAI.

View arXiv page View PDF Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.21791 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.21791 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.21791 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co