Animesh Garg

On leave

Faculty Member

Assistant Professor, Department of Computer Science, Faculty of Arts & Science, University of Toronto

Canada CIFAR Artificial Intelligence Chair

Senior Research Scientist, Nvidia

Assistant Professor (Courtesy), Mech & Industrial Engg., University of Toronto

Animesh is an Assistant Professor of Computer Science at the University of Toronto and a Faculty Member at the Vector Institute where he leads the Toronto People, AI, and Robotics (PAIR) research group. Animesh is affiliated with Mechanical and Industrial Engineering (courtesy) and UofT Robotics Institute. Animesh also spend time as a research scientist at Nvidia Research in ML for Robotics. Prior to this, Animesh was a postdoc at Stanford AI Lab. Animesh earned a Ph.D. from UC Berkeley, an MS from Georgia Institute of Technology and a BE from the University of Delhi.

Animesh’s research focuses on machine learning algorithms for perception and control in robotics. Animesh aim’s to enable Generalizable Autonomy through efficient robot learning for long-term sequential decision making. The principal technical focus lies in understanding representations and algorithms to enable simplicity and generality of learning for interaction in autonomous agents. Animesh actively works on applications of robot manipulation in industrial and healthcare robotics.

Research Interests

  • Robotics
  • Reinforcement learning
  • 3D vision
  • Optimal control

Publications

Conservative Safety Critics for Exploration

Homanga Bharadhwaj and Aviral Kumar and Nicholas Rhinehart and Sergey Levine and Florian Shkurti and Animesh Garg

2021

A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution

Valts Blukis and Chris Paxton and Dieter Fox and Animesh Garg and Yoav Artzi

2021

S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics

Samarth Sinha and Ajay Mandlekar and Animesh Garg

2021

Dynamics Randomization Revisited: A Case Study for Quadrupedal Locomotion

Zhaoming Xie and Xingye Da and Michiel van de Panne and Buck Babich and Animesh Garg

2021

DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting

Eric Heiden and Miles Macklin and Yashraj Narang and Dieter Fox and Animesh Garg and Fabio Ramos

2021

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Anuj Mahajan and Mikayel Samvelyan and Lei Mao and Viktor Makoviychuk and Animesh Garg and Jean Kossaifi and Shimon Whiteson and Yuke Zhu and Animashree Anandkumar

2021

Learning Latent Actions to Control Assistive Robots

Dylan P Losey and Hong Jun Jeon and Mengxi Li and Krishnan Srinivasan and Ajay Mandlekar and Animesh Garg and Jeannette Bohg and Dorsa Sadigh

2021

Robust Value Iteration for Continuous Control Tasks

Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg

2021

Skill Transfer via Partially Amortized Hierarchical Planning

Kevin Xie and Homanga Bharadhwaj and Danijar Hafner and Animesh Garg and Florian Shkurti

2021

Principled Exploration via Optimistic Bootstrapping and Backward Induction

Chenjia Bai and Lingxiao Wang and Lei Han and Jianye Hao and Animesh Garg and Peng Liu and Zhaoran Wang

2021

Value Iteration in Continuous Actions, States and Time

Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg

2021

LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

Arthur Allshire and Roberto Martín-Martín and Charles Lin and Shawn Manuel and Silvio Savarese and Animesh Garg

2021

Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers

Nikita Dvornik and Isma Hadji and Konstantinos G Derpanis and Animesh Garg and Allan D Jepson

2021

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

Bo Liu and Qiang Liu and Peter Stone and Animesh Garg and Yuke Zhu and Animashree Anandkumar

2021

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos

Haoyu Xiong and Quanzhou Li and Yun-Chun Chen and Homanga Bharadhwaj and Samarth Sinha and Animesh Garg

2021

Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects

Xinlei Pan and Animesh Garg and Animashree Anandkumar and Yuke Zhu

2021

GIFT: Generalizable Interaction-aware Functional Tool Affordances without Labels

Dylan Turpin and Liquan Wang and Stavros Tsogkas and Sven Dickinson and Animesh Garg

2021

LEAF: Latent Exploration Along the Frontier

Homanga Bharadhwaj and Animesh Garg and Florian Shkurti

2021

Dynamic Bottleneck for Robust Self-Supervised Exploration

Chenjia Bai and Lingxiao Wang and Lei Han and Animesh Garg and Jianye Hao and Peng Liu and Zhaoran Wang

2021

Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

Michael Poli and Stefano Massaroli and Luca Scimeca and Seong Joon Oh and Sanghyuk Chun and Atsushi Yamashita and Hajime Asama and Jinkyoo Park and Animesh Garg

2021

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

Panteha Naderian and Gabriel Loaiza-Ganem and Harry J Braviner and Anthony L Caterini and Jesse C Cresswell and Tong Li and Animesh Garg

2021

Machine learning using modular solution datasets

Ajay Uday Mandlekar and Fabio Tozeto Ramos and Byron Boots and GARG Animesh and Dieter Fox

2022

Online task inference for compositional tasks with context adaptation

GARG Animesh and Hongyu Ren and Yuke Zhu and Anima Anandkumar

2022

Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings

Matthew Shunshi Zhang and Murat Erdogdu and Animesh Garg

2022

Attribute-aware image generation using neural networks

Weili Nie and Tero Tapani Karras and Animesh Garg and Shoubhik Debnath and Anjul Patney and Anima Anandkumar

2022

Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects

Haoping Xu and Yi Ru Wang and Sagi Eppel and Alan Aspuru-Guzik and Florian Shkurti and Animesh Garg

2021

Generalizing Successor Features to continuous domains for Multi-task Learning

Melissa Mozifian and Dieter Fox and David Meger and Fabio Ramos and Animesh Garg

2021

Guided uncertainty-aware policy optimization: combining model-free and model-based strategies for sample-efficient learning

Jonathan Tremblay and Dieter Fox and Michelle Lee and Carlos Florensa and Nathan Donald Ratliff and Animesh Garg and Fabio Tozeto Ramos

2021