模拟世界中的自进化模仿学习
Self-evolved Imitation Learning in Simulated World
AI总结：
提出自进化模仿学习框架SEIL，通过模拟器交互和双层增强及轨迹筛选，在少样本场景下实现LIBERO基准上的最先进性能。
摘要：
模仿学习近年来成为研究趋势，然而，训练一个跨多任务的通用智能体仍需要大规模专家示范，这些示范的收集成本高昂且劳动密集。为解决监督有限这一挑战，我们提出了自进化模仿学习（SEIL），一种通过模拟器交互逐步改进少样本模型的框架。该模型首先在模拟器中尝试任务，从中收集成功的轨迹作为新的示范，用于迭代式优化。为增强这些示范的多样性，SEIL采用双层增强：（i）模型层面，使用指数移动平均（EMA）模型与主模型协作；（ii）环境层面，对初始物体位置引入微小变化。我们进一步引入一个轻量级选择器，从生成的轨迹池中筛选互补且信息量大的轨迹，以确保示范质量。这些精选样本使模型能够以更少的训练示例达到有竞争力的性能。在LIBERO基准上的大量实验表明，SEIL在少样本模仿学习场景中取得了新的最先进性能。代码可在https://github.com/Jasper-aaa/SEIL.git获取。
英文摘要：
Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited supervision, we propose Self-Evolved Imitation Learning (SEIL), a framework that progressively improves a few-shot model through simulator interactions. The model first attempts tasksin the simulator, from which successful trajectories are collected as new demonstrations for iterative refinement. To enhance the diversity of these demonstrations, SEIL employs dual-level augmentation: (i) Model-level, using an Exponential Moving Average (EMA) model to collaborate with the primary model, and (ii) Environment-level, introducing slight variations in initial object positions. We further introduce a lightweight selector that filters complementary and informative trajectories from the generated pool to ensure demonstration quality. These curated samples enable the model to achieve competitive performance with far fewer training examples. Extensive experiments on the LIBERO benchmark show that SEIL achieves a new state-of-the-art performance in few-shot imitation learning scenarios. Code is available at https://github.com/Jasper-aaa/SEIL.git.
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。
