Aravind Rajeswaran

PhD student in machine learning + robotics,
Computer Science & Engineering,
University of Washington

Contact: aravraj at cs.washington.edu
google scholar | github | calendar | twitter


I am a third year PhD student at UW with Sham Kakade and Emo Todorov. I also collaborate with Sergey Levine and his students. I am interested in the mathematical foundations and applications of machine learning. My current research leverages learning and optimization to endow robots with a vast repertoire of skills. To this end, I draw upon deep reinforcement learning, model-based control, and meta-learning.

I interned at Nvidia in Summer 2018 with Dieter Fox and Byron Boots. In summer 2017, I interned at OpenAI with Pieter Abbeel, John Schulman, and Igor Mordatch. Previously, I was an undergraduate student at IIT Madras, where I worked with Balaraman Ravindran. Before switching focus to AI, I worked on statistical physics of complex networks, and recieved the best undergraduate thesis award from IIT Madras.


News
  • Completed PhD qualifying exam in April 2019.
  • Organizing the workshop on generative modeling and model-based RL at ICML 2019.
  • Online Meta-Learning paper accepted at ICML 2019. Bringing meta-learning and online/lifelong learning closer.
  • POLO paper is accepted at ICLR 2019. Solve dexterous in-hand manipulation in < 20 mins on your laptop!
  • Two papers accepted at International Conference on Robotics and Automation (ICRA) 2019.

Representative Papers

Online Meta-Learning
Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine
International Conference on Machine Learning (ICML) 2019; arXiv:1902.08438

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch
International Conference on Learning Representations (ICLR) 2019; arXiv:1811.01848

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, John Schulman, Emanuel Todorov, Sergey Levine
Robotics: Science and Systems (RSS) 2018; arxiv:1709.10087

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system
Kendall Lowrey, Svetsolav Kolev, Jeremy Dao, Aravind Rajeswaran, Emanuel Todorov
IEEE SIMPAR 2018; arXiv:1803.10371 (Best paper award!)

Towards Generalization and Simplicity in Continuous Control
Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham Kakade
Neural Information Processing Systems (NIPS) 2017; arXiv:1703.02660


All Publications and Preprints

Online Meta-Learning
Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine
International Conference on Machine Learning (ICML) 2019; arXiv:1902.08438

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch
International Conference on Learning Representations (ICLR) 2019; arXiv:1811.01848

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low Cost
Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine, Vikash Kumar
International Conference on Robotics and Automation (ICRA) 2019; arXiv:1810.06045

Learning Deep Visuomotor Policies for Dexterous Hand Manipulation
Divye Jain, Andrew Li, Shivam Singhal, Aravind Rajeswaran, Vikash Kumar, Emanuel Todorov
International Conference on Robotics and Automation (ICRA) 2019; (pdf coming soon)

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system
Kendall Lowrey, Svetsolav Kolev, Jeremy Dao, Aravind Rajeswaran, Emanuel Todorov
IEEE SIMPAR 2018; arXiv:1803.10371 (Best paper award!)

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, John Schulman, Emanuel Todorov, Sergey Levine
Robotics: Science and Systems (RSS) 2018; arxiv:1709.10087

Variance Reduction for Policy Gradient Using Action-Dependent Factorized Baselines
Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M Bayen,
Sham Kakade, Igor Mordatch, Pieter Abbeel
International Conference on Learning Representations (ICLR) 2018; arXiv:1803.07246

Divide-and-Conquer Reinforcement Learning
Dibya Ghosh, Avi Singh, Aravind Rajeswaran, Vikash Kumar, Sergey Levine
International Conference on Learning Representations (ICLR) 2018; arXiv:1711.09874

Towards Generalization and Simplicity in Continuous Control
Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham Kakade
Neural Information Processing Systems (NIPS) 2017; arXiv:1703.02660

EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
Aravind Rajeswaran, Sarvjeet Ghotra, Balaraman Ravindran, Sergey Levine
International Conference on Learning Representations (ICLR) 2017; arXiv:1610.01283

A Novel Approach for Phase Identification in Smart Grids Using Graph Theory
and Principal Component Analysis

Satya Jayadev P, Aravind Rajeswaran, Nirav P Bhatt, Ramkrishna Pasumarthy
American Control Conference (ACC) 2016; arXiv:1511.06063

Identifying Topology of Power Distribution Networks Based on Smart Meter Data
Jayadev P Satya, Nirav Bhatt, Ramkrishna Pasumarthy, Aravind Rajeswaran
IEEE Transactions on Smart Grid 2017; arXiv:1609.02678

A Graph Partitioning Approach for Leak Detection in Water Distribution Networks
Aravind Rajeswaran, Sridharakumar Narasimhan, Shankar Narasimhan
Computers & Chemical Engineering (C&ChE) 2017; arXiv:1606.01754


Teaching

CSE599G: Deep Reinforcement Learning (Instructor)
I co-taught a course on deep reinforcement learning at UW in Spring 2018. The course takes a broad perspective on RL and covers topics including tabular dynamic programming, actor critic algorithms, trajectory optimization, MCTS, and guided policy search. I co-designed the course structure and all the teaching material. This course is inspired by the offerings of Emo Todorov, Balaraman Ravindran, and Sergey Levine.

CSE547: Machine Learning for Big Data (Teaching Assistant)


Mentoring

I enjoy collaborating with a diverse set of researchers, and have also had the pleasure of mentoring highly motivated undergraduate students. Some of them are:

  • Ben Evans, Colin Summers, and Brian Chan : model-based RL (w/ Kendall Lowrey)
  • Divye Jain : visual imitation learning