面向离线基于模型强化学习的时间距离感知转换增强方法
Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
AI总结：
针对离线基于模型强化学习在稀疏奖励长视野任务中表现不佳的问题，提出TempDATA框架，在时间结构化潜在空间生成增强转换并学习捕捉时间距离的潜在抽象，在多个基准上取得更优性能。
摘要：
离线强化学习（RL）的目标是从固定数据集中提取高性能策略，最大限度降低分布外（OOD）样本导致的性能下降。离线基于模型的强化学习（MBRL）是一种极具潜力的方法，它通过用经学习得到的动力学模型合成的增强样本丰富状态-动作转换，从而缓解OOD问题。遗憾的是，经典的离线MBRL方法往往在稀疏奖励、长视野任务中表现不佳。在本研究中，我们提出了一种名为Temporal Distance-Aware Transition Augmentation（TempDATA，时间距离感知转换增强）的新型MBRL框架，该框架在具有时间结构的潜在空间而非原始状态空间中生成增强转换。为了对长视野行为建模，TempDATA学习一种潜在抽象表征，该表征从状态空间的轨迹层和转换层两个层面捕捉时间距离。我们的实验证实，TempDATA性能优于此前的离线MBRL方法，并且在D4RL AntMaze、FrankaKitchen、CALVIN以及基于像素的FrankaKitchen基准上，性能达到或超过基于扩散的轨迹增强方法和目标条件RL方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
