OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

• URL: http://arxiv.org/abs/2604.02349v1
• Date: Thu, 19 Feb 2026 02:11:01 GMT
• Title: OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
• Abstract summary: Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions.<n>We propose a novel algorithm, textbfOffline textbfRL via textbfIn-textbfDataset textbfExploration (OPRIDE) to enhance the query efficiency of offline PbRL.
• Score: 42.70370800703202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpointing two primary reasons: inefficient exploration and overoptimization of learned reward functions. In response to these challenges, we propose a novel algorithm, \textbf{O}ffline \textbf{P}b\textbf{R}L via \textbf{I}n-\textbf{D}ataset \textbf{E}xploration (OPRIDE), designed to enhance the query efficiency of offline PbRL. OPRIDE consists of two key features: a principled exploration strategy that maximizes the informativeness of the queries and a discount scheduling mechanism aimed at mitigating overoptimization of the learned reward functions. Through empirical evaluations, we demonstrate that OPRIDE significantly outperforms prior methods, achieving strong performance with notably fewer queries. Moreover, we provide theoretical guarantees of the algorithm's efficiency. Experimental results across various locomotion, manipulation, and navigation tasks underscore the efficacy and versatility of our approach.

Related papers

• Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR [53.27792011950384]
  Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models.<n>We propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR.<n>Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts.
  arXiv  Detail & Related papers  (2026-05-15T08:22:59Z)
• Data-dependent Exploration for Online Reinforcement Learning from Human Feedback [50.34161049551627]
  Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously collecting new preference feedback during training.<n>Existing exploration strategies often derive bonuses via on-policy expectations, which are difficult to estimate reliably from the limited historical preference data available during training.<n>We propose data-dependent exploration for preference optimization (DEPO), a simple and scalable method that leverages historical data to construct an extra uncertainty bonus for high-uncertainty regions.
  arXiv  Detail & Related papers  (2026-05-06T03:56:45Z)
• Preference-Guided Reinforcement Learning for Efficient Exploration [14.058764537783086]
  We introduce LOPE: textbfLearning textbfOnline with trajectory textbfPreferencedanctextbfE, an end-to-end preference-guided RL framework.<n>Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance.<n>LOPE outperforms several state-of-the-art methods in terms of convergence rate and overall performance.
  arXiv  Detail & Related papers  (2024-07-09T02:11:12Z)
• A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems [67.52782366565658]
  State-of-the-art recommender systems (RSs) depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables.<n>Despite the prosperity of lightweight embedding-based RSs, a wide diversity is seen in evaluation protocols.<n>This study investigates various LERS' performance, efficiency, and cross-task transferability via a thorough benchmarking process.
  arXiv  Detail & Related papers  (2024-06-25T07:45:00Z)
• On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning [1.3381647310440739]
  Potential-Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL)<n>We first build some theoretically-grounded intuition on why selecting the potential function as the optimal value function of the task at hand produces performance advantages.<n>We then analyse the bias induced by finite horizons in the context of PBRS producing novel insights.
  arXiv  Detail & Related papers  (2024-04-11T15:09:49Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• Query-Policy Misalignment in Preference-Based Reinforcement Learning [21.212703100030478]
  We show that the seemingly informative queries selected to improve the overall quality of reward model actually may not align with RL agents' interests. We show that this issue can be effectively addressed via near on-policy query and a specially designed hybrid experience replay. Our method achieves substantial gains in both human feedback and RL sample efficiency.
  arXiv  Detail & Related papers  (2023-05-27T07:55:17Z)
• Efficient Online Reinforcement Learning with Offline Data [78.92501185886569]
  We show that we can simply apply existing off-policy methods to leverage offline data when learning online. We extensively ablate these design choices, demonstrating the key factors that most affect performance. We see that correct application of these simple recommendations can provide a $mathbf2.5times$ improvement over existing approaches.
  arXiv  Detail & Related papers  (2023-02-06T17:30:22Z)
• Open Problems and Modern Solutions for Deep Reinforcement Learning [0.0]
  We review two publications that investigate the mentioned issues of DRL and propose effective solutions. One designs the reward for human-robot collaboration by combining the manually designed extrinsic reward with a parameterized intrinsic reward function. The other one applies selective attention and particle filters to rapidly and flexibly attend to and select crucial pre-learned features for DRL using approximate inference instead of backpropagation.
  arXiv  Detail & Related papers  (2023-02-05T04:42:42Z)
• Controlled Deep Reinforcement Learning for Optimized Slice Placement [0.8459686722437155]
  We present a hybrid ML-heuristic approach that we name "Heuristically Assisted Deep Reinforcement Learning (HA-DRL)" The proposed approach leverages recent works on Deep Reinforcement Learning (DRL) for slice placement and Virtual Network Embedding (VNE) The evaluation results show that the proposed HA-DRL algorithm can accelerate the learning of an efficient slice placement policy.
  arXiv  Detail & Related papers  (2021-08-03T14:54:00Z)

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.