Robust Optimization for Mitigating Reward Hacking with Correlated Proxies

• URL: http://arxiv.org/abs/2604.12086v1
• Date: Mon, 13 Apr 2026 21:47:49 GMT
• Title: Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
• Abstract summary: We formulate reward hacking as a robust policy optimization problem over the space of all r-correlated proxy rewards.<n>Our algorithms consistently outperform ORPO in worst-case returns, and offer improved robustness and stability across different levels of proxy-true reward correlation.
• Score: 8.966550940372967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them vulnerable to reward hacking, where high proxy returns arise from unintended or exploitative behaviors. Recent work formalizes this issue using r-correlation between proxy and true rewards, but existing methods like occupancy-regularized policy optimization (ORPO) optimize against a fixed proxy and do not provide strong guarantees against broader classes of correlated proxies. In this work, we formulate reward hacking as a robust policy optimization problem over the space of all r-correlated proxy rewards. We derive a tractable max-min formulation, where the agent maximizes performance under the worst-case proxy consistent with the correlation constraint. We further show that when the reward is a linear function of known features, our approach can be adapted to incorporate this prior knowledge, yielding both improved policies and interpretable worst-case rewards. Experiments across several environments show that our algorithms consistently outperform ORPO in worst-case returns, and offer improved robustness and stability across different levels of proxy-true reward correlation. These results show that our approach provides both robustness and transparency in settings where reward design is inherently uncertain. The code is available at https://github.com/ZixuanLiu4869/reward_hacking.

Related papers

• Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search [8.82040111147814]
  We present an end-to-end RLAIF framework to generate emphportable search queries.<n>This task introduces a highly adversarial reward surface where policy optimization exploits flaws in rubrics, resulting in verbatim-copying behaviors.<n>We show that introducing a rule-based reward floor to correct for rewards assigned to verbatim copying degenerates this failure mode, resulting in a substantial $+0.147$ quality improvement on a cross-family evaluation judge.
  arXiv  Detail & Related papers  (2026-06-25T17:09:12Z)
• IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking [67.20568716300272]
  Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking.<n>We introduce IR3 (Interpretable Reward Reconstruction and Rectification), a framework that reverse-engineers, interprets, and surgically repairs the implicit objectives driving RLHF-tuned models.<n>We show that IR3 achieves 0.89 correlation with ground-truth rewards, identifies hacking features with over 90% precision, and significantly reduces hacking behaviors while maintaining capabilities within 3% of the original model.
  arXiv  Detail & Related papers  (2026-02-23T01:14:53Z)
• Unifying Stable Optimization and Reference Regularization in RLHF [64.16830602324345]
  This paper introduces a unified regularization approach that balances objectives of preventing reward hacking and maintaining stable policy updates.<n>Our simple yet principled alignment objective yields a weighted supervised fine-tuning loss with a superior trade-off, which demonstrably improves both alignment results and implementation complexity.
  arXiv  Detail & Related papers  (2026-02-12T03:31:19Z)
• GARDO: Reinforcing Diffusion Models without Reward Hacking [54.841464430913476]
  Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment.<n>The mismatch often leads to reward hacking, where proxy scores increase while real image quality deteriorates and generation diversity collapses.<n>We propose Gated and Adaptive Regularization with Diversity-aware Optimization (GARDO) to address the competing demands of sample efficiency, effective exploration, and mitigation of reward hacking.
  arXiv  Detail & Related papers  (2025-12-30T10:55:45Z)
• Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm [24.126318783226598]
  Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations.<n>Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization.<n>Recent non-adversarial IRL approaches improve stability by jointly learning reward and policy via energy-based formulations.
  arXiv  Detail & Related papers  (2025-09-27T05:36:13Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Inference-Time Reward Hacking in Large Language Models [29.829648695171425]
  Reward models function as proxies for complex desiderata such as correctness, helpfulness, and safety.<n>By overoptimizing for a misspecified reward, we can subvert intended alignment goals and reduce overall performance.<n>We show that hedging mitigates reward hacking and achieves superior reward-distortion tradeoffs on math, reasoning, and human-preference setups.
  arXiv  Detail & Related papers  (2025-06-24T02:05:25Z)
• Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning [14.852334980733369]
  Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning.<n>We introduce Temporal-Agent Reward Redistribution (TAR$2$), an approach that decouples credit modeling from this constraint.<n>We demonstrate that this method is equivalent to a valid Potential-Based Reward Shaping (PBRS), which guarantees the optimal policy is preserved regardless of model accuracy.
  arXiv  Detail & Related papers  (2025-02-07T12:07:57Z)
• Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking [11.589217788048964]
  We introduce a definition of reward hacking based on the correlation between proxy and true rewards for states.<n>We show theoretically that regularization to the reference policy can effectively prevent reward hacking.
  arXiv  Detail & Related papers  (2024-03-05T18:22:15Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
  We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk. Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
  arXiv  Detail & Related papers  (2021-06-11T16:49:15Z)

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.