Researcher Pieter Abbeel

Researcher Biography
http://www.eecs.berkeley.edu/Faculty/Homepages/abbeel.html

Current Projects

Few-Shot Imitation and Embodiment Transfer
Learning Video Models Using VQ-VAE and Transformers
Uncertainty-Aware Reinforcement Learning for Interaction-Intensive Driving Tasks

Past Projects

Best of both Worlds: Combining Classical Planning with Learning for Long-horizon Tasks
Auto-tuned Sim-to-Real Transfer
Self-driving by multi-objective reinforcement learning with goal-conditioned policies
Towards ​safe​ self-driving by reinforcement learning with maximization of diversity of future options
Life-Long Learning to Drive by Semi-Supervised Reinforcement Learning (SSRL)
Model-Based Reinforcement Learning
Deep Reinforcement Learning for Robot Navigation
Adversarial Examples in Reinforcement Learning and Imitation Learning
Acting and Learning under Uncertainty
Enabling Passenger Comfort by Increasing Behavior Transparency
Robotic Assembly from CAD