GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL

• URL: http://arxiv.org/abs/2602.05323v1
• Date: Thu, 05 Feb 2026 05:44:48 GMT
• Title: GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL
• Authors: Zifan Liu, Xinran Li, Shibo Chen, Jun Zhang,
• Abstract summary: Offline Safe Reinforcement Learning (OSRL) aims to learn a policy to achieve high performance in decision-making while satisfying constraints.<n>Recent works, inspired by the strong capabilities of Generative Models (GMs), reformulate decision-making in OSRL as a conditional generative process.<n>We propose Goal-Assisted Stitching (GAS), a novel algorithm designed to enhance stitching capabilities while effectively balancing reward and constraint satisfaction.
• Score: 21.30558932544297
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Offline Safe Reinforcement Learning (OSRL) aims to learn a policy to achieve high performance in sequential decision-making while satisfying constraints, using only pre-collected datasets. Recent works, inspired by the strong capabilities of Generative Models (GMs), reformulate decision-making in OSRL as a conditional generative process, where GMs generate desirable actions conditioned on predefined reward and cost values. However, GM-assisted methods face two major challenges in OSRL: (1) lacking the ability to "stitch" optimal transitions from suboptimal trajectories within the dataset, and (2) struggling to balance reward targets with cost targets, particularly when they are conflict. To address these issues, we propose Goal-Assisted Stitching (GAS), a novel algorithm designed to enhance stitching capabilities while effectively balancing reward maximization and constraint satisfaction. To enhance the stitching ability, GAS first augments and relabels the dataset at the transition level, enabling the construction of high-quality trajectories from suboptimal ones. GAS also introduces novel goal functions, which estimate the optimal achievable reward and cost goals from the dataset. These goal functions, trained using expectile regression on the relabeled and augmented dataset, allow GAS to accommodate a broader range of reward-cost return pairs and achieve a better tradeoff between reward maximization and constraint satisfaction compared to human-specified values. The estimated goals then guide policy training, ensuring robust performance under constrained settings. Furthermore, to improve training stability and efficiency, we reshape the dataset to achieve a more uniform reward-cost return distribution. Empirical results validate the effectiveness of GAS, demonstrating superior performance in balancing reward maximization and constraint satisfaction compared to existing methods.

Related papers

• Constraint-Aware Generative Auto-bidding via Pareto-Prioritized Regret Optimization [8.514099612407062]
  PRO-Bid is a constraint-aware generative auto-bidding framework based on two synergistic mechanisms.<n>It achieves superior constraint satisfaction and value acquisition compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-09T04:41:30Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents [28.145430029174577]
  Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments.<n>Existing approaches typically rely on outcome-based rewards that are only provided at the final answer.<n>In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training.
  arXiv  Detail & Related papers  (2025-10-16T17:59:32Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• Reinforced Preference Optimization for Recommendation [28.87206911186567]
  We propose Reinforced Preference Optimization for Recommendation (ReRe) for generative recommenders.<n>ReRe incorporates constrained beam search to improve sampling efficiency and diversify hard negatives.<n>We show that ReRe consistently outperforms both traditional and LLM-based recommenders in ranking performance.
  arXiv  Detail & Related papers  (2025-10-14T07:04:33Z)
• Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment [51.10604883057508]
  We propose DR-IRL (Dynamically adjusting Rewards through Inverse Reinforcement Learning)<n>We first train category-specific reward models using a balanced safety dataset covering seven harmful categories via IRL.<n>Then we enhance Group Relative Policy Optimization (GRPO) by introducing rewards by task difficulty--data-level hardness by text encoder cosine similarity, model-level responsiveness by reward gaps.
  arXiv  Detail & Related papers  (2025-03-23T16:40:29Z)
• Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning [17.245293915129942]
  The optimal objective is a fundamental aspect of reinforcement learning (RL)<n>While total return is ideal, discounted return is practical objective due to its stability.<n>We propose two alternative approaches to align the objectives.
  arXiv  Detail & Related papers  (2024-07-18T08:33:10Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)

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.