Inverse RL Helps Align AI by Imitating Humans

• URL: http://arxiv.org/abs/2607.24900v1
• Date: Mon, 27 Jul 2026 16:45:31 GMT
• Title: Inverse RL Helps Align AI by Imitating Humans
• Abstract summary: Projected Alignment Reward Estimated from Demonstrations (PARED)<n>We show that PARED recovers the implicit reward underlying expert demonstrations as an explicit function over a small set of response-level features.<n>We also demonstrate that PARED can be used for contextual alignment, in which a single policy can be tailored to the preferences of different audiences.
• Score: 8.637696682498076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language model alignment aims to make model behavior reliably reflect desirable properties such as helpfulness, safety, and instruction following. Current approaches typically use supervised fine-tuning on demonstrations or reinforcement learning with rewards derived from verifiers or human feedback. These paradigms leave an important question underexplored: can demonstrations alone yield an implicit reward that can be inspected, reused, and optimized on-policy to align AI? Motivated by inverse reinforcement learning, we introduce Projected Alignment Reward Estimated from Demonstrations (PARED). PARED recovers the implicit reward underlying expert demonstrations as an explicit function over a small set of response-level features, learned by a lightweight discriminator that separates demonstrations from the policy's own samples in this feature space. Unlike a standard reward model, PARED requires no task-specific preference annotations: demonstrations provide the task-specific supervision, which can be augmented with AI feedback as additional dimensions of supervision. Through experiments involving inference-time reranking and adversarial on-policy RL, we show that the recovered reward improves a base policy without a supervised loss and yields further gains when optimized after standard supervised fine-tuning. Additionally, we demonstrate that PARED can be used for contextual alignment, in which a single policy can be tailored to the preferences of different audiences.

Related papers

• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation [50.696688705287755]
  We propose Mutual Information Self-Evaluation to overcome the sparse reward challenge in reinforcement learning.<n>MISE enables an agent to learn autonomously from dense internal rewards supplementing sparse extrinsic signals.<n>We prove that utilizing hindsight self-evaluation rewards is equivalent to minimizing an objective that combines mutual information with a KL divergence term between the policy and a proxy reward policy.
  arXiv  Detail & Related papers  (2026-04-13T15:18:51Z)
• Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention [29.17663968152743]
  We propose entropy-guided adversarial sampling (EgAS) that formu- lates the entropy of sampled responses as an adversarial ob- jective.<n>The corresponding adversarial gradient can be used to attack the visual input for producing adversarial samples, allowing the policy model to explore a larger an- swer space during RL sampling.
  arXiv  Detail & Related papers  (2025-12-11T08:27:02Z)
• Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning [50.20267980386502]
  We learn a dense, token-level reward model for process supervision directly from expert demonstrations.<n>The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets.
  arXiv  Detail & Related papers  (2025-10-02T09:55:26Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs [25.011675414622392]
  This study introduces a novel approach to enhance the reward model's generalization ability against distribution shifts. We retain the base model's language model head and incorporate a suite of text-generation losses to preserve the hidden states' text-generation capabilities. Our experimental results demonstrate that the introduced regularization technique markedly improves the accuracy of learned reward models.
  arXiv  Detail & Related papers  (2024-06-14T17:49:59Z)
• Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges.<n>We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals.<n> Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Aligning Large Language Models by On-Policy Self-Judgment [49.31895979525054]
  Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. We present a novel alignment framework, SELF-JUDGE, that does on-policy learning and is parameter efficient. We show that the rejecting sampling by itself can improve performance further without an additional evaluator.
  arXiv  Detail & Related papers  (2024-02-17T11:25:26Z)
• Residual Reinforcement Learning from Demonstrations [51.56457466788513]
  Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn from visual inputs and sparse rewards using demonstrations. Our experimental evaluation on simulated manipulation tasks on a 6-DoF UR5 arm and a 28-DoF dexterous hand demonstrates that residual RL from demonstrations is able to generalize to unseen environment conditions more flexibly than either behavioral cloning or RL fine-tuning.
  arXiv  Detail & Related papers  (2021-06-15T11:16:49Z)

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.