通过时间感知的潜在空间增强，提升离线模型强化学习在长周期任务中的表现。
Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
- 在潜在空间中按时间距离生成增强转移，避免原始状态空间的分布偏差。
- 在D4RL AntMaze等任务上超越现有离线MBRL方法，媲美扩散模型与目标条件RL。
- 适合处理稀疏奖励、长周期决策的离线强化学习场景，尤其适用于机器人控制。
离线强化学习的目标是从固定数据集中提取高性能策略，减少因分布外（OOD）样本导致的性能下降。离线模型基础强化学习（MBRL）通过学习动态模型合成增强的状态-动作转移来缓解OOD问题。然而，经典方法在稀疏奖励、长周期任务中表现不佳。本文提出一种新框架TempDATA，它在时序结构化的潜在空间中生成增强转移，而非原始状态空间。为建模长周期行为，TempDATA学习一种潜在抽象，同时捕捉轨迹和转移层面的时间距离。实验表明，TempDATA优于以往离线MBRL方法，在D4RL AntMaze、FrankaKitchen、CALVIN及基于像素的FrankaKitchen任务上达到或超过基于扩散模型的轨迹增强和目标条件强化学习的性能。
原文摘要 · Abstract (English)
The goal of offline reinforcement learning (RL) is to extract a high-performance policy from the fixed datasets, minimizing performance degradation due to out-of-distribution (OOD) samples. Offline model-based RL (MBRL) is a promising approach that ameliorates OOD issues by enriching state-action transitions with augmentations synthesized via a learned dynamics model. Unfortunately, seminal offline MBRL methods often struggle in sparse-reward, long-horizon tasks. In this work, we introduce a novel MBRL framework, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates augmented transitions in a temporally structured latent space rather than in raw state space. To model long-horizon behavior, TempDATA learns a latent abstraction that captures a temporal distance from both trajectory and transition levels of state space. Our experiments confirm that TempDATA outperforms previous offline MBRL methods and achieves matching or surpassing the performance of diffusion-based trajectory augmentation and goal-conditioned RL on the D4RL AntMaze, FrankaKitchen, CALVIN, and pixel-based FrankaKitchen.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。