cs.LGNov 5, 2026

Provable Zeroth-Order Safe Exploration for Reinforcement Learning from Human Feedback

Authors: Weiqin Chen, Xinmeng Huang, Dongsheng Ding, Santiago Paternain

Organizations: Purdue University · UPenn · University of Tennessee, Knoxville · RPI

Abstract

Safe reinforcement learning from human feedback (Safe-RLHF) seeks to improve helpfulness while satisfying harmlessness constraints. Existing primal-dual approaches can converge to feasible policies but do not prevent constraint violations during training. We study a stronger requirement, safe exploration for RLHF, under which every policy executed during training, including auxiliary exploration policies, remains feasible. We propose Zeroth-Order Log-Barrier Policy Gradient (ZO-LBPG), a reward-model-free method that optimizes a log-barrier objective using zeroth-order estimates derived directly from human preferences. To ensure safety under noisy feedback, we combine conservative constraint margin estimates with coupled rollouts and an adaptive step size that prevents updates from crossing constraint boundaries. We prove that, with high probability, all iterates and exploration policies remain strictly feasible, and that ZO-LBPG globally converges to an approximately optimal constrained policy. We establish a sample complexity of O~(ε−6+d3ε−5)\widetilde{\mathcal O}(\varepsilon^{-6}+d^3\varepsilon^{-5}) trajectories and O~(ε−8+d5ε−7)\widetilde{\mathcal O}(\varepsilon^{-8}+d^5\varepsilon^{-7}) human queries. Experiments on a synthetic CMDP and a language-model alignment task corroborate the training-time safety guarantees.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 21, 2026

Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback

Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language models by decoupling human preferences regarding helpfulness and harmlessness. Existing approaches typically rely on fitting fixed horizon reward models from human feedback and have only been validated empirically. In this paper, we formulate safe RLHF as an infinite horizon discounted Con- strained Markov Decision Process (CMDP), since humans may interact with the model over a continuing sequence of interactions rather than within a single finite episode. We propose two Safe RLHF algorithms that do not require reward model fitting and, in contrast to prior work assuming fixed-length trajectories, support flexible trajectory lengths for training. Both algo- rithms are based on the primal-dual method and achieve global convergence guarantees with polynomial rates in terms of policy gradient iterations, trajectory sample lengths, and human preference queries. To the best of our knowledge, this is the first work to study infinite horizon discounted CMDP under human feedback and establish global, non-asymptotic convergence.
May 19, 2026

Sampling-Based Safe Reinforcement Learning

Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a finite set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty, eliminating the need for explicit exploration bonuses. Under regularity conditions, we derive high-probability guarantees of safety throughout learning and a finite-time sample complexity bound for recovering a near-optimal policy. Empirically, SBSRL achieves safe and efficient exploration both in simulation and in real robotic hardware, and readily extends to practical deep-ensemble implementations that scale to high-dimensional continuous control problems.
Dec 29, 2025

SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints

In safety-critical domains, reinforcement learning (RL) systems must satisfy strict, zero-cost safety constraints while achieving meaningful task performance. Existing model-free methods can struggle to achieve high safety without substantially compromising task performance. We introduce Safety-Biased Trust Region Policy Optimisation (SB-TRPO), a principled approach to RL with zero-cost constraints, which requires only a fixed fraction of the maximal cost reduction achievable within the trust region, thus retaining flexibility for reward optimisation. We show that the idealised update nevertheless converges to zero cost and maximal reward amongst zero-cost policies in finite MDPs. A practical gradient-based approximation provides local improvements in both safety and reward under suitable gradient alignment. Experiments on Safety Gymnasium demonstrate high safety alongside strong task performance.