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

• URL: http://arxiv.org/abs/2604.19024v1
• Date: Tue, 21 Apr 2026 03:20:07 GMT
• Title: Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback
• Abstract summary: We formulate safe RLHF as an infinite horizon discounted Con- strained Decision Process (CMDP)<n>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.<n>To the best of our knowledge, this is the first work to study infinite CMDP under human feedback and establish global, non-asymptotic convergence.
• Score: 11.48153290349358
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual [26.51548597257528]
  We introduce an optimistic primal-dual (OPD) algorithm that incorporates predictive updates for both primal and dual variables to stabilize saddle-point dynamics.<n>Our analysis reveals that optimism plays a crucial role in mitigating oscillations inherent to constrained alignment objectives.
  arXiv  Detail & Related papers  (2026-02-25T17:54:52Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [15.038210624870656]
  Reward inference is a critical intermediate step in the Reinforcement Learning from Human Feedback pipeline.<n>This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDP bandit, and general preference models beyond the Bradley-Terry model.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models [94.39278422567955]
  Fine-tuning large language models (LLMs) on human preferences has proven successful in enhancing their capabilities.<n>However, ensuring the safety of LLMs during fine-tuning remains a critical concern.<n>We propose a supervised learning framework called Bi-Factorial Preference Optimization (BFPO) to address this issue.
  arXiv  Detail & Related papers  (2024-08-27T17:31:21Z)
• One-Shot Safety Alignment for Large Language Models via Optimal Dualization [64.52223677468861]
  This paper presents a perspective of dualization that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. Our strategy leads to two practical algorithms in model-based and preference-based settings.
  arXiv  Detail & Related papers  (2024-05-29T22:12:52Z)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation [24.374185140811115]
  Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. We propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one.
  arXiv  Detail & Related papers  (2024-04-30T23:57:23Z)
• Nash Learning from Human Feedback [86.09617990412941]
  We introduce an alternative pipeline for the fine-tuning of large language models using pairwise human feedback. We term this approach Nash learning from human feedback (NLHF) We present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent.
  arXiv  Detail & Related papers  (2023-12-01T19:26:23Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism [91.52263068880484]
  We study offline Reinforcement Learning with Human Feedback (RLHF) We aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF is challenging for multiple reasons: large state space but limited human feedback, the bounded rationality of human decisions, and the off-policy distribution shift.
  arXiv  Detail & Related papers  (2023-05-29T01:18:39Z)
• Provable Offline Preference-Based Reinforcement Learning [95.00042541409901]
  We investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback. We consider the general reward setting where the reward can be defined over the whole trajectory. We introduce a new single-policy concentrability coefficient, which can be upper bounded by the per-trajectory concentrability.
  arXiv  Detail & Related papers  (2023-05-24T07:11:26Z)

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.