Interactive Robot Learning – Stanford ILIAD

Stanford Intelligent and Interactive Autonomous Systems Group

Data Quality in Imitation Learning HYDRA improves the sample efficiency for learning real world long-horizon tasks by modifying robot action spaces to reduce online distribution shift. In robotics, scaling up data collection for imitation learning is often challenging, and our test settings are constantly shifting from the training data. Therefore, if we want robots to learn new tasks scalably, we need to be more sample efficient with both learning methods and the type of data we collect. We study the interaction between models and data sources for learning manipulation tasks in robotics,…

related reading

• State of Robot Learning, December 2025vedder.io
• Ch. 21 - Imitation Learningunderactuated.mit.edu
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• Open X-Embodiment: Robotic Learning Datasets and RT-X Modelsarxiv.org
• ALOHA Unleashed: A Simple Recipe for Robot Dexterityaloha-unleashed.github.io
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• Learning Latent Plans from Playlearning-from-play.github.io
• So You Think You Can Scale Up Autonomous Robot Data Collection?arxiv.org
• Many Small Steps for Robots, One Giant Leap for Mankindnotboring.co
• Supervised Policy Learning for Real Robotssupervised-robot-learning.github.io
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• Neural Motionneural-motion.com