Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

• URL: http://arxiv.org/abs/2410.19933v1
• Date: Fri, 25 Oct 2024 19:08:23 GMT
• Title: Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
• Authors: Xiyue Peng, Hengquan Guo, Jiawei Zhang, Dongqing Zou, Ziyu Shao, Honghao Wei, Xin Liu,
• Abstract summary: We propose textbfRectified Policy Optimization (RePO), which replaces the average safety constraint with stricter (per prompt) safety constraints. At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt. Our experiments on Alpaca-7B demonstrate that RePO improves the safety alignment and reduces the safety interference compared to baseline methods.
• Score: 16.35399722653875
• License:
• Abstract: Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while framing safety as a constraint within a constrained Markov Decision Process (CMDP) framework. However, these methods can lead to ``safety interference'', where average-based safety constraints compromise the safety of some prompts in favor of others. To address this issue, we propose \textbf{Rectified Policy Optimization (RePO)}, which replaces the average safety constraint with stricter (per prompt) safety constraints. At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt, thereby enhancing safety across nearly all prompts. Our experiments on Alpaca-7B demonstrate that RePO improves the safety alignment and reduces the safety interference compared to baseline methods. Code is available at https://github.com/pxyWaterMoon/RePO.

Related papers

• Embedding Safety into RL: A New Take on Trust Region Methods [1.5733417396701983]
  Reinforcement Learning (RL) agents are able to solve a wide variety of tasks but are prone to unsafe behaviors. We propose Constrained Trust Region Policy Optimization (C-TRPO), a novel approach that modifies the geometry of the policy space based on the safety constraints.
  arXiv  Detail & Related papers  (2024-11-05T09:55:50Z)
• Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
  "Shielding" is a popular technique to enforce safety inReinforcement Learning (RL) We propose a new permissibility-based framework to deal with safety and shield construction.
  arXiv  Detail & Related papers  (2024-05-29T18:00:21Z)
• Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching [77.36097118561057]
  textscSafePatching is a novel framework for comprehensive and efficient PSA. textscSafePatching achieves a more comprehensive and efficient PSA than baseline methods.
  arXiv  Detail & Related papers  (2024-05-22T16:51:07Z)
• Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints [15.904640266226023]
  We design a safety model that performs credit assignment to assess contributions of partial state-action trajectories on safety. We derive an effective algorithm for optimizing a safe policy using the learned safety model. We devise a method to dynamically adapt the tradeoff coefficient between safety reward and safety compliance.
  arXiv  Detail & Related papers  (2024-05-05T17:27:22Z)
• Enhancing LLM Safety via Constrained Direct Preference Optimization [8.22888921018027]
  We introduce Constrained DPO (C-DPO), a novel extension of the recently proposed Direct Preference Optimization (DPO) approach for fine-tuning AI systems. By integrating dual gradient descent and DPO, our method identifies a nearly optimal trade-off between helpfulness and harmlessness without using reinforcement learning. Empirically, our approach provides a safety guarantee to LLMs that is missing in DPO while achieving significantly higher rewards under the same safety constraint.
  arXiv  Detail & Related papers  (2024-03-04T20:39:24Z)
• Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning [64.11013095004786]
  We propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2022-12-14T03:11:25Z)
• Safe Policy Improvement in Constrained Markov Decision Processes [10.518340300810504]
  We present a solution to the synthesis problem by solving its two main challenges: reward-shaping from a set of formal requirements and safe policy update. For the former, we propose an automatic reward-shaping procedure, defining a scalar reward signal compliant with the task specification. For the latter, we introduce an algorithm ensuring that the policy is improved in a safe fashion with high-confidence guarantees.
  arXiv  Detail & Related papers  (2022-10-20T13:29:32Z)
• Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
  We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
  arXiv  Detail & Related papers  (2022-09-29T20:49:25Z)
• Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
  We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-07-04T11:43:23Z)
• Enhancing Safe Exploration Using Safety State Augmentation [71.00929878212382]
  We tackle the problem of safe exploration in model-free reinforcement learning. We derive policies for scheduling the safety budget during training. We show that Simmer can stabilize training and improve the performance of safe RL with average constraints.
  arXiv  Detail & Related papers  (2022-06-06T15:23:07Z)
• Lyapunov Barrier Policy Optimization [15.364174084072872]
  We propose a new method, LBPO, that uses a Lyapunov-based barrier function to restrict the policy update to a safe set for each training iteration. Our method also allows the user to control the conservativeness of the agent with respect to the constraints in the environment.
  arXiv  Detail & Related papers  (2021-03-16T17:58:27Z)

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.