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 & contextSergey Levine
Learning robot behavior from data with deep reinforcement learning.
Levine studies how robots and other agents can learn behavior from data. The selected papers connect deep reinforcement learning and reusable skills with generalist robot policies that combine vision, language, and action.
Selected work
10 papers
2018 · 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 & context2022 · Robotics
RT-1: Robotics Transformer for Real-World Control at Scale
RT-1 uses a robotics transformer trained on diverse real-world demonstrations to map camera images and instructions to robot actions, studying generalization and control at scale.
Paper & context2023 · Robotics
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
RT-2 transfers knowledge from vision-language models into robotic control by representing actions in a compatible format.
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
Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Language models
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
Selected research in language models, robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?
Selected research in robotics. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Robotics
Adapting Generalist Robot Policies with Semantic Reinforcement Learning
Selected research in 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