Pieter Abbeel
Robots That Learn
Deep reinforcement learning for real machines
Rating
85Impact score
Domains
RoboticsReinforcement learningImitation learning
Scouting report
Berkeley professor who moved deep RL out of simulators and onto physical robots, with apprenticeship learning, domain randomisation and the BAIR lab’s long run of open releases. Co-founded Covariant, and his Deep RL Bootcamp and course materials are freely available and are how a lot of people learned the subject.
Curator’s note
The bridge between a policy that works in sim and an arm that works.
Portrait
Painted from a photograph of Pieter Abbeel by Pieterabbeel, licensed CC BY-SA 4.0.
Sources
- 01Pieter Abbeel en.wikipedia.org
- 02Berkeley Artificial Intelligence Research bair.berkeley.edu