Repairing Reward Functions with Human Feedback to Mitigate Reward Hacking

• URL: http://arxiv.org/abs/2510.13036v1
• Date: Tue, 14 Oct 2025 23:18:24 GMT
• Title: Repairing Reward Functions with Human Feedback to Mitigate Reward Hacking
• Authors: Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, Emma Brunskill,
• Abstract summary: We propose an automated framework that repairs a human-specified proxy reward function by learning an additive, transition-dependent correction term from preferences.<n>PBRR consistently outperforms baselines that learn a reward function from scratch from preferences or modify the proxy reward function using other approaches.
• Score: 13.417125511014447
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces reward hacking, resulting in a policy misaligned with the human's true objectives. An alternative is to perform RL from human feedback, which involves learning a reward function from scratch by collecting human preferences over pairs of trajectories. However, building such datasets is costly. To address the limitations of both approaches, we propose Preference-Based Reward Repair (PBRR): an automated iterative framework that repairs a human-specified proxy reward function by learning an additive, transition-dependent correction term from preferences. A manually specified reward function can yield policies that are highly suboptimal under the ground-truth objective, yet corrections on only a few transitions may suffice to recover optimal performance. To identify and correct for those transitions, PBRR uses a targeted exploration strategy and a new preference-learning objective. We prove in tabular domains PBRR has a cumulative regret that matches, up to constants, that of prior preference-based RL methods. In addition, on a suite of reward-hacking benchmarks, PBRR consistently outperforms baselines that learn a reward function from scratch from preferences or modify the proxy reward function using other approaches, requiring substantially fewer preferences to learn high performing policies.

Related papers

• Reward-Conditioned Reinforcement Learning [56.417273471201845]
  We introduce Reward-Conditioned Reinforcement Learning (RCRL), a framework that trains a single agent to optimize a family of reward specifications.<n>RCRL conditions the agent on reward parameterizations and learns multiple reward objectives from a shared replay data entirely off-policy.<n>Our results demonstrate that RCRL provides a scalable mechanism for learning robust, steerable policies without sacrificing the simplicity of single-task training.
  arXiv  Detail & Related papers  (2026-03-05T11:29:17Z)
• 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)
• PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning [29.373324685358753]
  We propose PROF, a framework to generate and improve executable reward function codes from natural language descriptions and a single expert trajectory.<n>We also propose Reward Preference Ranking (RPR), a novel reward function quality assessment and ranking strategy without requiring environment interactions or RL training.
  arXiv  Detail & Related papers  (2025-11-14T14:38:02Z)
• 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)
• TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning [48.31236495564408]
  This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI)<n>TROFI is a novel approach to effectively learn a policy offline without a pre-defined reward function.<n>We show that TROFI consistently outperforms baselines and performs comparably to using the ground truth reward to learn policies.
  arXiv  Detail & Related papers  (2025-06-27T08:22:41Z)
• Hindsight PRIORs for Reward Learning from Human Preferences [3.4990427823966828]
  Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem inherent in determining which parts of a behavior most contributed to a preference. We introduce a credit assignment strategy (Hindsight PRIOR) that uses a world model to approximate state importance within a trajectory and then guides rewards to be proportional to state importance.
  arXiv  Detail & Related papers  (2024-04-12T21:59:42Z)
• 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)
• 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)
• Mind the Gap: Offline Policy Optimization for Imperfect Rewards [14.874900923808408]
  We propose a unified offline policy optimization approach, textitRGM (Reward Gap Minimization), which can handle diverse types of imperfect rewards. By exploiting the duality of the lower layer, we derive a tractable algorithm that enables sampled-based learning without any online interactions.
  arXiv  Detail & Related papers  (2023-02-03T11:39:50Z)
• Reward Uncertainty for Exploration in Preference-based Reinforcement Learning [88.34958680436552]
  We present an exploration method specifically for preference-based reinforcement learning algorithms. Our main idea is to design an intrinsic reward by measuring the novelty based on learned reward. Our experiments show that exploration bonus from uncertainty in learned reward improves both feedback- and sample-efficiency of preference-based RL algorithms.
  arXiv  Detail & Related papers  (2022-05-24T23:22:10Z)

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.