Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret

• URL: http://arxiv.org/abs/2603.20453v1
• Date: Fri, 20 Mar 2026 19:34:53 GMT
• Title: Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret
• Abstract summary: We study episodic RL from emphmulti-source imperfect preferences through a cumulative imperfection budget.<n>We propose a unified algorithm with regret $tildeO(sqrtK/M+)$, which exhibits a best-of-both-regimes behavior.
• Score: 71.69884486156359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth objective. In practical RLHF systems, however, feedback is typically \emph{multi-source} (annotators, experts, reward models, heuristics) and can exhibit systematic, persistent mismatches due to subjectivity, expertise variation, and annotation/modeling artifacts. We study episodic RL from \emph{multi-source imperfect preferences} through a cumulative imperfection budget: for each source, the total deviation of its preference probabilities from an ideal oracle is at most $ω$ over $K$ episodes. We propose a unified algorithm with regret $\tilde{O}(\sqrt{K/M}+ω)$, which exhibits a best-of-both-regimes behavior: it achieves $M$-dependent statistical gains when imperfection is small (where $M$ is the number of sources), while remaining robust with unavoidable additive dependence on $ω$ when imperfection is large. We complement this with a lower bound $\tildeΩ(\max\{\sqrt{K/M},ω\})$, which captures the best possible improvement with respect to $M$ and the unavoidable dependence on $ω$, and a counterexample showing that naïvely treating imperfect feedback as as oracle-consistent can incur regret as large as $\tildeΩ(\min\{ω\sqrt{K},K\})$. Technically, our approach involves imperfection-adaptive weighted comparison learning, value-targeted transition estimation to control hidden feedback-induced distribution shift, and sub-importance sampling to keep the weighted objectives analyzable, yielding regret guarantees that quantify when multi-source feedback provably improves RLHF and how cumulative imperfection fundamentally limits it.

Related papers

• A Regret Minimization Framework on Preference Learning in Large Language Models [33.19510618137341]
  Reinforcement learning with verifiable rewards has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers.<n>Many realistic language tasks are difficult to equip with reliable verifiers, motivating a growing reliance on reinforcement learning from human feedback.<n>We introduce Regret-based Preference Optimization $(textbfRePO)$, which reframes RLHF through $textitregret$ rather than reward-independent minimization.
  arXiv  Detail & Related papers  (2026-06-08T07:18:44Z)
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL [71.6241143519038]
  Reinforcement learning has become the dominant approach for aligning diffusion models with human preferences.<n>Existing practice deal with multiple rewards by training one specialist model per reward.<n>We propose MARBLE, a gradient-space optimization framework that maintains independent advantage estimators for each reward.
  arXiv  Detail & Related papers  (2026-05-07T16:20:42Z)
• Singular Bayesian Neural Networks [1.2891210250935148]
  Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors.<n>We induce a posterior that is singular with respect to the Lebesgue measure, concentrating on the rank-$r$ manifold.<n>We derive PAC-Bayes generalization bounds whose complexity term scales as $sqrtr(m+n)$ instead of $sqrtm n$, and prove loss bounds that decompose the error into optimization and rank-induced bias.
  arXiv  Detail & Related papers  (2026-01-30T23:06:34Z)
• ZIP-RC: Optimizing Test-Time Compute via Zero-Overhead Joint Reward-Cost Prediction [57.799425838564]
  We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost.<n> ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost.
  arXiv  Detail & Related papers  (2025-12-01T09:44:31Z)
• DRO-REBEL: Distributionally Robust Relative-Reward Regression for Fast and Efficient LLM Alignment [0.0]
  Reinforcement learning with human feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent.<n>We introduce DRO-REBEL, a unified family of robust REBEL updates with type-$p$ Wasserstein, KL, and $chi2$ ambiguity sets.<n>Using Fenchel duality, each update reduces to a simple relative-reward regression, preserving scalability and avoiding PPO-style clipping or auxiliary value networks.
  arXiv  Detail & Related papers  (2025-09-23T14:49:48Z)
• Robust Reinforcement Learning from Corrupted Human Feedback [86.17030012828003]
  Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. We propose a robust RLHF approach -- $R3M$, which models the potentially corrupted preference label as sparse outliers. Our experiments on robotic control and natural language generation with large language models (LLMs) show that $R3M$ improves robustness of the reward against several types of perturbations to the preference data.
  arXiv  Detail & Related papers  (2024-06-21T18:06:30Z)
• Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption [60.958746600254884]
  This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL) We introduce an algorithm called corruption-robust optimistic MLE (CR-OMLE), which leverages total-variation (TV)-based information ratios as uncertainty weights for MLE. We extend our weighting technique to the offline setting, and propose an algorithm named corruption-robust pessimistic MLE (CR-PMLE)
  arXiv  Detail & Related papers  (2024-02-14T07:27:30Z)
• Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning [52.76230802067506]
  A novel model-free algorithm is proposed to minimize regret in episodic reinforcement learning. The proposed algorithm employs an em early-settled reference update rule, with the aid of two Q-learning sequences. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings.
  arXiv  Detail & Related papers  (2021-10-09T21:13:48Z)
• Rethinking gradient sparsification as total error minimization [0.0]
  Gradient compression is a widely-established remedy to tackle the communication bottleneck in distributed training training networks (DNNs) We argue that the benefits of gradient sparsification, especially for DNNs, are necessary -- one that moves from perit optimality to consider optimality for the entire training.
  arXiv  Detail & Related papers  (2021-08-02T14:52:42Z)
• Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards [24.983866845065926]
  We consider multi-armed bandits with heavy-tailed rewards, whose $p$-th moment is bounded by a constant $nu_p$ for $1pleq2$. We propose a novel robust estimator which does not require $nu_p$ as prior information. We show that an error probability of the proposed estimator decays exponentially fast.
  arXiv  Detail & Related papers  (2020-10-24T10:44:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.