Group

Current

Post-docs

Jongmin Lee

Youngwoon Lee

Xingyu Lin

Aravind Rajeswaran(v)

Carlo Sferrazza

Ph.D. students

Ademi Adeniji	Xinyue Chen	Yuqing Du	Alejandro Escontrela
Jakub (Kuba) Grudzien	Ajay Jain	Fangchen Liu	Hao Liu
Amy Lu	Olivia Watkins	Philipp Wu	Wilson Yan
Sherry Yang	Kevin Zakka
Danijar Hafner (v)	Younggyo Seo (v)	Denis Yarats (v)

Undergraduate students

Anthony Han (2024)	Aryan Jain (2024)	Vint Lee (2024)	Sashwat Mahalingam (2024)
John So (2023)	Meiqi Sun (2024)	Amber Xie (2023)

On Leave

Former

Post-docs

Ph.D. students

Kourosh Hakhamaneshi (May 2022)
Thesis: Pre-training Agents for Design Optimization and Control
Next: Anyscale

Xue Bin (Jason) Peng (December 2021)
Thesis: Acquiring Motor Skills Through Motion Imitation and Reinforcement Learning
Next:

Roshan Rao
Thesis: Training, Evaluating, and Understanding Evolutionary Models for Protein Sequences
Next: Facebook AI Research

Aravind Srinivas (August 2021)
Thesis: Representation Learning for Perception and Control
Next: Research Scientist at OpenAI

Abhishek Gupta (August 2021)
Thesis: How to Train Your Robot: Techniques for Enabling Robotic Learning in the Real World
Next: Post-doc at MIT
Next-next: Assistant Professor at University of Washington

Thanard Kurutach (May 2021)
Thesis: Learning, Planning, and Acting with Models
Next: Research Scientist at Cruise

Joshua Achiam (May 2021)
Thesis: Exploration and Safety in Deep Reinforcement Learning
Next: Research Scientist at OpenAI

Gregory Kahn (December 2020)
Thesis: Mobile Robot Learning
Next: stealth start-up

Ignasi Clavera (August 2020)
Thesis: Overcoming Model-Bias in Reinforcement Learning
Next: Research Scientist at Covariant

Coline Devin (August 2020)
Thesis: Compositionality and Modularity for Robot Learning
Next: Research Scientist at Deepmind

Dylan Hadfield-Menell (August 2020)
Thesis: The Principal-Agent Alignment Problem in Artificial Intelligence
Next: Assistant Professor at MIT

Rohin Shah (August 2020)
Thesis: Extracting and Using Preference Information from the State of the World
Next: Research Scientist at Deepmind

Adam Stooke (August 2020)
Thesis: Advancements in Deep Reinforcement Learning: Algorithms and Implementations
Next: Research Scientist at Deepmind

Carlos Florensa Campo (May 2020)
Thesis: What Supervision Scales? Practical Learning Through Interaction
Next: Research Scientist at Covariant.AI

Jonathan Ho (May 2020)
Thesis: Deep Generative Models: Imitation Learning, Image Synthesis, and Compression
Next: Research Scientist at Google Brain (Amsterdam)

Alex Lee (May 2019)
Thesis: Visual Dynamics Models for Robotic Planning and Control
Next: Research Scientist at Deepmind

Sandy Huang (May 2019)
Thesis: Optimizing for Robot Transparency
Next: Research Scientist at Deepmind

Haoran Tang (May 2019)
Thesis: Towards Informed Exploration for Deep Reinforcement Learning
Next: Research Scientist at Covariant.AI

Josh Tobin (May 2019)
Thesis: Real-World Robotics Perception and Control Using Synthetic Data
Next: Research Scientist at OpenAI

Tuomas Haarnoja (December 2018)
Thesis: Acquiring Diverse Robot Skills via Maximum Entropy Deep Reinforcement Learning
Next: Research Scientist at Deepmind

Chelsea Finn (August 2018)
Thesis: Learning to Learn with Gradients
Next: Research Scientist at Google Brain | Post-doc at Berkeley
Next next: Assistant Professor at Stanford University

Bradly Stadie (August 2018)
Thesis: Learning as a Sampling Problem
Next: Post-doc at the University of Toronto

Yan (Rocky) Duan (December 2017)
Thesis: Meta-Learning for Control
Next: Founder / CTO Covariant.AI

John Schulman (December 2016)
Thesis: Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs
Next: Founder / Research Scientist OpenAI

Karthik Narayan (December 2016)
Thesis: Scalable High-Quality 3D Scanning (Thesis talk: pdf, pptx)
Next: Algorithm Developer (aka Quantitative Analyst) at Hudson River Trading LLC

Arjun Singh (August 2016)
Thesis: Benchmarks for Cloud Robotics
Next: Founder / CEO Gradescope

Jeremy Maitin-Shepard (December 2015)
Thesis: Machine Learning and Optimization for Neural Circuit Reconstruction
Next: Google

Tim Hunter (primary advisor: Alex Bayen) (August 2014)
Thesis: Large-Scale, Low-Latency State Estimation Of Cyber-Physical Systems With An Application To Traffic Estimation
Next: DataBricks

Teodor Moldovan (May 2014)
Thesis: Safety, Risk Awareness and Exploration in Reinforcement Learning
Next: Voleon

Woody Hoburg (August 2013)
Thesis: Aircraft Design Optimization as a Geometric Program
Next: One year at Boeing and then Assistant Professor at MIT starting Fall 2014

Aude Hofleitner (primary advisor: Alex Bayen) (May 2013)
Thesis: A Hybrid Approach of Physical Laws and Data-Driven Modeling for Estimation: the Example of Queuing Networks
Next: Facebook

Visitors and Volunteers

Masters students

Undergraduate students