This work proposes a general RL-based framework for Distribution Matching allowing matching the distribution of a latent categorical attribute of model outputs to a specified target distribution and proposes reward functions for other divergences such as KL and Jensen-Shannon and motivate them with theoretical justification.
Abstract
Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from binary verifiers or reward models trained on human feedback. However, applications such as synthetic-data generation, fairness-related constraint satisfaction, and policy exploration require controlling the distribution of outputs across model generations rather than only maximizing expected reward. We propose a general RL-based framework for \textit{Distribution Matching} allowing matching the distribution of a latent categorical attribute of model outputs to a specified target distribution. Empirically, we demonstrate that dominant post-training recipes such as Group Relative Policy Optimization (GRPO) reduce output diversity by concentrating policy probability towards a single mode. Entropy regularization and sampling temperature can improve the spread of the distribution but have constrained effectiveness, limited to apply only in token space and toward uniform distributions. We show that prior work in this area is a specific case of Distribution Matching involving the $L_2$ divergence. We then propose reward functions for other divergences such as KL and Jensen-Shannon and motivate them with theoretical justification. Finally, we demonstrate the effectiveness of our approach on a set of experiments involving mathematical reasoning and programming.
Reinforcement Learning (RL)-based post-training has become a key mechanism for improving reasoning Large Language Models (LLMs), especially when automated verifiers enable Reinforcement Learning with Verifiable Reward (RLVR). Recent methods, however, are increasingly modular: many apparent algorithmic advances recombin...
Liu Yang, Han Zhu, Zheng-Yang Zhong et al.· International Conference on...· 2 citations
Best Practice Critic Optimization (BPCO) is developed, a recipe that combines DPPO, value predictions bounded to the reward range, Monte Carlo value targets, unnormalized policy advantages, and length-adaptive generalized advantage estimation and shows that a carefully designed critic provides a reliable alternative to...
CIS replaces the unbounded second moment that governs the error of exact importance sampling with a term bounded by a constant, at the cost of a bias controlled by the truncated excess, in evaluation across three mixture-of-experts models and five mathematical reasoning benchmarks.
Tian-Run Yu, Kai-Xiang Zhao, Shang-Zhe Li et al.· arXiv.org· 1 citation
Temperature-Grouped Reinforcement Learning (TGRL), which turns temperature-induced diversity into an explicit training signal, and reaches equivalent accuracy up to 36% faster than strong RLVR baselines without expanding the rollout budget.
Zi-Han Lin, Xiao-Han Wang, Jie Cao et al.· arXiv.org· 0 citations
Policy Aligned Critic Training (PACT), which adopts an Actor-then-Critic update order to apply importance sampling correction to critic training and better align the critic with the updated policy, is developed.
Jia-Yan Fu, Hang Xu, Yong Zhang et al.· arXiv.org· 0 citations
ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact on performance, and it also provides a unified view (as we show in this work) to understand prediction losses heuristically chosen in prior...
Qin-Wei Ma, Jing-Zhe Shi, Si-Min Fan et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.