Papers
Sign in to view your remaining parses.
Tag Filter
Imitation Learning
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
Published:3/23/2022
Adversarial Motion PriorsRobotic Locomotion ControlImitation LearningDiverse Skill LearningReinforcement Learning
This study presents MultiAMP, an enhanced adversarial motion prior method that simplifies reward function tuning in reinforcement learning for robotic motion control. Experiments demonstrate simultaneous learning of multiple styles and skills without significant performance diff
04
TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot
Learning
Published:12/12/2024
Robotic Action LearningImitation LearningMobile Manipulator DesignHolonomic Mobile BaseLLM-guided motion planning
TidyBot is an opensource, lowcost holonomic mobile manipulator using powered casters for full planar freedom, enabling agile motion and simplified tasks. A phone teleoperation interface facilitates data collection for imitation learning, achieving successful household manipul
04
Robot (Imitation) Learning
Published:6/1/1999
Robotic Action LearningImitation LearningBehavioral CloningMultimodal Demonstration Dataset
This work introduces behavioral cloning for robot imitation learning, leveraging offline multimodal expert demonstrations without reward design, enabling safe, direct observationtoaction mapping and overcoming realworld reinforcement learning challenges.
04
Robot Learning: A Tutorial
Published:10/14/2025
Robotic Action LearningGeneralist Robot PoliciesReinforcement Learning TrainingImitation LearningLLM-guided motion planning
This tutorial presents core robot learning methods, from reinforcement learning and behavioral cloning to generalist languageconditioned policies, enabling better generalization and autonomy across diverse tasks and embodiments using datadriven approaches and lerobot examples.
04
MimicGen: A Data Generation System for Scalable Robot Learning using
Human Demonstrations
Published:10/27/2023
Robotic Action LearningImitation LearningRobot Demonstration Dataset GenerationMulti-Task Robot LearningAutomated Data Synthesis System
MimicGen automatically generates large, diverse robot datasets from limited human demos, enabling scalable robot learning with strong performance in complex tasks, matching the effectiveness of extensive human demonstrations economically.
02