关于KL正则化策略优化的研究

arXiv:2610.08963v1 Announce Type: new Abstract: Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the trainer's even at identical parameters. Standard remedies either clip importance ratios, which biases the update, or, as in GRPO, sample a group of responses per prompt, which is costly when episodes are long. We propose KL-Regularized Policy Optimization (KLPO), a framework that anchors the KL regularizer at the sampler. The regularized improvement step then has a closed-form Gibbs solution, and KLPO fits its log-ratio optimality condition by least squares on the sampler's own trajectories, so the sampler probability enters through a log-ratio and no importance weights are needed. Profiling out the regression intercept replaces the intractable log-partition function with the signal's sampler mean plus a sampler-to-trainer KL divergence. For token-level policy mirror descent targets, we show that the resulting gradient can be computed from terminal returns without a critic, via sampler-centered scores or a single trajectory residual, even under stochastic tool outputs. We further prove that independent Monte Carlo estimates of the KL term keep these gradients unbiased, derive the exact KL gap of cheaper top-$K$ and binary approximations, and show that SPPO, GPO, REBEL, and BPO arise as special cases of KLPO. The result is a critic-free update that uses one rollout per prompt and requires neither a learned normalizer nor a group of responses.

# On KL-Regularized Policy Optimization
Source: [https://arxiv.org/abs/2610.08963](https://arxiv.org/abs/2610.08963)
Bibliographic Tools

## Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Code, Data, Media

## Code, Data and Media Associated with this Article

Demos

## Demos

Related Papers

## Recommenders and Search Tools

IArxiv recommender toggle

About arXivLabs

## arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website\.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy\. arXiv is committed to these values and only works with partners that adhere to them\.

Have an idea for a project that will add value for arXiv's community?[**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html)\.