$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
Abstract
Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inherited from pre-training. In this work, we introduce , a value-based algorithm for KL-regularized RL that guides the reference policy using the optimal regularized function. We propose to learn the optimal function using distributional RL on an aggregated online dataset. Unlike prior value-based baselines that guide the model using unregularized -values, our method is theoretically principled and provably learns the optimal policy for the KL-regularized RL problem. Empirically, outperforms prior baselines in math reasoning benchmarks while maintaining a smaller KL divergence to the reference policy. Theoretically, we establish a reduction from KL-regularized RL to no-regret online learning, providing the first bounds for deterministic MDPs under only realizability. Thanks to distributional RL, our bounds are also variance-dependent and converge faster when the reference policy has small variance. In sum, our results highlight as an effective approach for post-training LLMs, offering both improved performance and theoretical guarantees. The code can be found at https://github.com/jinpz/q_sharp.
Cite
@article{arxiv.2502.20548,
title = {$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training},
author = {Jin Peng Zhou and Kaiwen Wang and Jonathan Chang and Zhaolin Gao and Nathan Kallus and Kilian Q. Weinberger and Kianté Brantley and Wen Sun},
journal= {arXiv preprint arXiv:2502.20548},
year = {2025}
}
Comments
NeurIPS 2025