让智能体跨域模仿专家动作，从视觉中提取不变特征。
Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations
- 逐帧提取跨域不变特征，再组装成序列
- 通过时间标签划分行为阶段，提升模仿精度
- 适合视觉观测复杂、数据不完整的跨域场景
模仿学习（IL）使智能体无需奖励信号即可模仿专家行为，但在高维、噪声大且不完整的视觉观测下存在跨域挑战。为此，我们提出一种新方法——针对模仿学习的域不变逐帧特征提取（DIFF-IL），从单帧中提取域不变特征，并将其转化为序列以分离并复现专家行为。同时引入逐帧时间标记技术，按时间步分割专家行为并分配与上下文一致的奖励，从而提升任务表现。在多种视觉环境下的实验表明，DIFF-IL在处理复杂视觉任务时具有显著有效性。
原文摘要 · Abstract (English)
Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete visual observations. To address this, we propose Domain-Invariant Per-Frame Feature Extraction for Imitation Learning (DIFF-IL), a novel IL method that extracts domain-invariant features from individual frames and adapts them into sequences to isolate and replicate expert behaviors. We also introduce a frame-wise time labeling technique to segment expert behaviors by timesteps and assign rewards aligned with temporal contexts, enhancing task performance. Experiments across diverse visual environments demonstrate the effectiveness of DIFF-IL in addressing complex visual tasks.
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。