Researcher Sergey Levine

Researcher Biography

https://people.eecs.berkeley.edu/~svlevine/

Current Projects

Factual, Controllable, and Interactive Dialogue Agents

Sequence Modeling as Reinforcement Learning

Past Projects

Offline Reinforcement Learning for Data-Driven Autonomous Driving

Off-Policy Reinforcement Learning for Learning from Logged Data

Uncertainty-Aware Meta-Learning and Safe Adaptation

Learning Human-Like Decision-making Behavior based on Adversarial Inverse Reinforcement Learning

Imitative Models: Learning Flexible Driving Models from Human Data

Uncertainty-Aware End-to-End Prediction for Robust Decision Making

Model-based Reinforcement Learning in a Latent Space

Deep RL with Dexterous Hands and Tactile Sensing

Hierarchical Reinforcement Learning & Abstraction Discovery

Training Real-World Robotic Skills in Diverse Simulated Environments