cs.AI updates on arXiv.org 07月31日 12:47
GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文介绍了一种名为GABRIL的模仿学习方法,通过分析人类注视数据来指导表征学习,从而减少因果混淆,提升测试环境中的性能。

arXiv:2507.19647v1 Announce Type: cross Abstract: Imitation Learning (IL) is a widely adopted approach which enables agents to learn from human expert demonstrations by framing the task as a supervised learning problem. However, IL often suffers from causal confusion, where agents misinterpret spurious correlations as causal relationships, leading to poor performance in testing environments with distribution shift. To address this issue, we introduce GAze-Based Regularization in Imitation Learning (GABRIL), a novel method that leverages the human gaze data gathered during the data collection phase to guide the representation learning in IL. GABRIL utilizes a regularization loss which encourages the model to focus on causally relevant features identified through expert gaze and consequently mitigates the effects of confounding variables. We validate our approach in Atari environments and the Bench2Drive benchmark in CARLA by collecting human gaze datasets and applying our method in both domains. Experimental results show that the improvement of GABRIL over behavior cloning is around 179% more than the same number for other baselines in the Atari and 76% in the CARLA setup. Finally, we show that our method provides extra explainability when compared to regular IL agents.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

模仿学习 注视数据 GABRIL 性能提升 因果混淆
相关文章