2020 · Diffusion
Denoising Diffusion Probabilistic Models
Denoising diffusion probabilistic models learn to generate data by reversing a noise-adding process. This became a foundation of modern image generation.
Paper & contextPieter Abbeel
Learning policies for difficult perception and control problems.
Abbeel’s research connects learning algorithms with difficult perception and control problems. These papers span robot learning, policy optimization, meta-learning, and generative models. A recurring theme is learning useful behavior from limited demonstrations and experience.
Selected work
10 papers
2017 · Robotics
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2015 · Reinforcement learning
Trust Region Policy Optimization
Selected research in reinforcement learning, robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2018 · Robotics
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Soft Actor-Critic combines off-policy learning with an objective that rewards both successful actions and policy entropy.
Paper & context2023 · Robotics
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment combines robotic data across embodiments to study generalization and reusable robot policies.
Paper & context2026 · Robotics
Humanoid Safe Stop via Learned Stoppability Value
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
Scalable Behavior Cloning with Open Data, Training, and Evaluation
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Computer vision
T-Rex: Tactile-Reactive Dexterous Manipulation
Selected research in computer vision, robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources