通过扩散薛定谔桥跨领域强化学习弥合动态缺口
Bridging Dynamics Gaps via Diffusion Schrödinger Bridge for Cross-Domain Reinforcement Learning
AI总结：
BDGxRL通过扩散薛定谔桥对齐源域与目标域动态，利用离线演示实现跨领域强化学习策略学习，优于现有基线并具备强适应性。
摘要：
跨领域强化学习（RL）旨在在源域和目标域之间动态偏移下学习可转移的策略。一个关键挑战在于缺乏目标域环境交互和奖励监督，这阻止了直接策略学习。为了解决这一挑战，我们提出了Bridging Dynamics Gaps for Cross-Domain Reinforcement Learning（BDGxRL），一种新颖的框架，利用扩散薛定谔桥（DSB）来对齐源转换与目标域动态编码在离线演示中的动态。此外，我们引入了一种奖励调节机制，该机制基于状态转换估计奖励，应用于DSB对齐的样本以确保奖励与目标域动态的一致性。BDGxRL在源域内完全执行目标导向的策略学习，而无需访问目标环境或其奖励。在MuJoCo跨领域基准测试中，BDGxRL优于最先进的基线，并在转换动态偏移下表现出强大的适应性。
英文摘要：
Cross-domain reinforcement learning (RL) aims to learn transferable policies under dynamics shifts between source and target domains. A key challenge lies in the lack of target-domain environment interaction and reward supervision, which prevents direct policy learning. To address this challenge, we propose Bridging Dynamics Gaps for Cross-Domain Reinforcement Learning (BDGxRL), a novel framework that leverages Diffusion Schrödinger Bridge (DSB) to align source transitions with target-domain dynamics encoded in offline demonstrations. Moreover, we introduce a reward modulation mechanism that estimates rewards based on state transitions, applying to DSB-aligned samples to ensure consistency between rewards and target-domain dynamics. BDGxRL performs target-oriented policy learning entirely within the source domain, without access to the target environment or its rewards. Experiments on MuJoCo cross-domain benchmarks demonstrate that BDGxRL outperforms state-of-the-art baselines and shows strong adaptability under transition dynamics shifts.
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。
