Researcher Pieter Abbeel

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

Current Projects

Best of both Worlds: Combining Classical Planning with Learning for Long-horizon Tasks
Life-Long Learning to Drive by Semi-Supervised Reinforcement Learning (SSRL)
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
Uncertainty-Aware Reinforcement Learning for Interaction-Intensive Driving Tasks

Past Projects

Acting and Learning under Uncertainty
Adversarial Examples in Reinforcement Learning and Imitation Learning
Deep Reinforcement Learning for Robot Navigation
Enabling Passenger Comfort by Increasing Behavior Transparency
Model-Based Reinforcement Learning
Robotic Assembly from CAD