Deepali Jain
I completed my undergraduate degree in Electrical Engineering from Indian Institute of Technology Roorkee. After that, I worked as a Research Fellow in Adobe Research for two years. There, I worked on problems in the area of sequence modeling and human decision making.
I have now developed a research interest in Reinforcement Learning (RL). I am motivated by the prospect that RL can serve as a general framework for solving intelligent decision-making problems across domains. More specifically, I am interested in addressing research challenges of partial observability, sparse rewards, sample inefficiency, multiple goals and multi-agent dynamics. In general, I like to think and read about ways to advance machine cognition.
The Google AI residency program has provided me with the right environment and mentorship to develop my research skills. I am collaborating with the Robotics NY team to improve sample efficiency of RL algorithms for legged locomotion task. My mentors welcome new ideas from me and guide me to the right direction for further exploration. Google’s infrastructure makes trying out experiments very easy. It is exciting to tackle challenges in deploying policies on a real robot. I am enjoying this learning experience.
Outside work, I love creating art, reading and exploring the city.
Research Areas
Authored Publications
Sort By
Google
Agile Catching with Whole-Body MPC and Blackbox Policy Learning
Saminda Abeyruwan
Nick Boffi
Anish Shankar
Jean-Jacques Slotine
Stephen Tu
Learning for Dynamics and Control (2023)
Robotic Table Tennis: A Case Study into a High Speed Learning System
Jon Abelian
Saminda Abeyruwan
Michael Ahn
Justin Boyd
Erwin Johan Coumans
Omar Escareno
Wenbo Gao
Navdeep Jaitly
Juhana Kangaspunta
Satoshi Kataoka
Gus Kouretas
Yuheng Kuang
Corey Lynch
Thinh Nguyen
Ken Oslund
Barney J. Reed
Anish Shankar
Avi Singh
Grace Vesom
Peng Xu
Robotics: Science and Systems (2023)
Hybrid Random Features
Haoxian Chen
Han Lin
Yuanzhe Ma
Arijit Sehanobish
Michael Ryoo
Jake Varley
Andy Zeng
Valerii Likhosherstov
Dmitry Kalashnikov
Adrian Weller
International Conference on Learning Representations (ICLR) (2022)
i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops
Saminda Wishwajith Abeyruwan
Avi Singh
Anish Shankar
Conference on Robot Learning (Oral) (2022)
Reward Machines for Vision-Based Robotic Manipulation.
Alberto Camacho
Andy Zeng
Dmitry Kalashnikov
Jake Varley
International Conference on Robotics and Automation (2021)
Learning to walk on complex terrains with vision
Ale Escontrela
Erwin Johan Coumans
Peng Xu
Sehoon Ha
Conference on Robotic Learning (2021)
Disentangled Planning and Control in Vision Based Robotics via Reward Machines
Alberto Camacho
Andy Zeng
Dmitry Kalashnikov
Jake Varley
Deep Reinforcement Learning Workshop (Deep RL), collocated with NeurIPS 2020 (2020)
Provably Robust Blackbox Optimization for Reinforcement Learning
Aldo Pacchiano
Jack Parker-Holder
Yunhao Tang
Yuxiang Yang
Conference on Robot Learning (CoRL 2019)
