Fewer May Be Better: Enhancing Offline Reinforcement Learning With Reduced Dataset

Abstract

Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environment. A key, yet underexplored, challenge in offline RL is selecting an optimal subset of the offline dataset that enhances both algorithm performance and training efficiency. Reducing dataset size can also reveal the minimal data requirements necessary for solving similar problems. In response to this challenge, we introduce ReDOR (Reduced Datasets for Offline RL), a method that frames dataset selection as a gradient approximation optimization problem. We demonstrate that the widely used actor-critic framework in RL can be reformulated as a submodular optimization objective, enabling efficient subset selection. To achieve this, we adapt orthogonal matching pursuit (OMP), incorporating several novel modifications tailored for offline RL. Our experimental results show that the data subsets identified by ReDOR

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2025fewer

Related papers

• An Optimistic Perspective On Offline Reinforcement Learning (2019)0.00
• Don't Change The Algorithm, Change The Data: Exploratory Data For Offline Reinforcement Learning (2022)0.00
• Leveraging Offline Data In Online Reinforcement Learning (2022)0.00
• Data-efficient Pipeline For Offline Reinforcement Learning With Limited Data (2022)0.00
• AWAC: Accelerating Online Reinforcement Learning With Offline Datasets (2020)0.00
• Optimality Inductive Biases And Agnostic Guidelines For Offline Reinforcement Learning (2021)0.00
• Efficient Online Reinforcement Learning Fine-tuning Need Not Retain Offline Data (2024)0.00
• Data Valuation For Offline Reinforcement Learning (2022)0.00