Imitation Learning
Imitation learning aims to train agents to mimic expert behavior by learning from observational data, primarily focusing on efficiently transferring complex skills from humans or other advanced controllers to robots. Current research emphasizes improving data efficiency through techniques like active learning, data augmentation, and leveraging large language models to provide richer context and handle failures. This field is crucial for advancing robotics, autonomous driving, and other areas requiring complex control policies, as it offers a more data-driven and potentially less labor-intensive approach than traditional programming methods.
Papers
RoboCLIP: One Demonstration is Enough to Learn Robot Policies
Sumedh A Sontakke, Jesse Zhang, Sébastien M. R. Arnold, Karl Pertsch, Erdem Bıyık, Dorsa Sadigh, Chelsea Finn, Laurent Itti
Imitation Learning from Observation with Automatic Discount Scheduling
Yuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao
Imitation Learning from Purified Demonstration
Yunke Wang, Minjing Dong, Bo Du, Chang Xu
Memory-Consistent Neural Networks for Imitation Learning
Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman, James Weimer, Insup Lee
Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond
Hao Sun
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
Xiong-Hui Chen, Junyin Ye, Hang Zhao, Yi-Chen Li, Haoran Shi, Yu-Yan Xu, Zhihao Ye, Si-Hang Yang, Anqi Huang, Kai Xu, Zongzhang Zhang, Yang Yu
Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies
Iman Sharifi, Saber Fallah
Development of a Whole-body Work Imitation Learning System by a Biped and Bi-armed Humanoid
Yutaro Matsuura, Kento Kawaharazuka, Naoki Hiraoka, Kunio Kojima, Kei Okada, Masayuki Inaba
In-Hand Re-grasp Manipulation with Passive Dynamic Actions via Imitation Learning
Dehao Wei, Guokang Sun, Zeyu Ren, Shuang Li, Zhufeng Shao, Xiang Li, Nikos Tsagarakis, Shaohua Ma