I am interested in building generalist agents that are capable of solving any task of interest. To that end, my work focuses on
unlocking generalization in robot learning by enabling agents to efficiently explore in the real world, leveraging hierarchy to quickly solve new tasks,
performing imitation learning at scale to train powerful generalist agents and integrating large-scale learning into hierarchical systems to enable broadly capable manipulation systems.
Here is some of my work (representative papers are highlighted):
|
Local Policies Enable Zero-shot Long-horizon Manipulation
Murtaza Dalal*,
Min Liu*,
Walter Talbott,
Chen Chen,
Deepak Pathak,
Jian Zhang,
Ruslan Salakhutdinov,
CoRL Learning Embodied Abstractions for Planning Workshop, 2024 (Oral)
arXiv |
site |
video
|
|
Neural MP: A Generalist Neural Motion Planner
Murtaza Dalal*,
Jiahui Yang*,
Russell Mendonca,
Youssef Khaky,
Ruslan Salakhutdinov,
Deepak Pathak
arXiv |
site |
code |
video
|
|
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
Murtaza Dalal*,
Tarun Chiruvolu,
Devendra Chaplot,
Ruslan Salakhutdinov
International Conference on Learning Representations (ICLR), 2024
arXiv |
site |
code
|
|
Imitating Task and Motion Planning with Visuomotor Transformers
Murtaza Dalal,
Ajay Mandlekar*,
Caelan Garrett*,
Ankur Handa,
Ruslan Salakhutdinov,
Dieter Fox
Conference on Robot Learning (CoRL), 2023
arXiv |
site |
code
|
|
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency
Devendra Chaplot*
Murtaza Dalal, Saurabh Gupta, Jitendra Malik, Ruslan Salakhutdinov
Neural Information Processing Systems (NeurIPS), 2021
arXiv |
site |
video
|
|
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives
Murtaza Dalal*, Deepak Pathak, Ruslan Salakhutdinov
Neural Information Processing Systems (NeurIPS), 2021
arXiv |
site |
code
|
|
Accelerating Online Reinforcement Learning with Offline Datasets
Ashvin Nair*, Abhishek Gupta*, Murtaza Dalal, Sergey Levine
arXiv |
site |
code |
blog
|
|
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
Vitchyr H. Pong*, Murtaza
Dalal*, Steven Lin*, Ashvin Nair, Shikhar Bahl, Sergey Levine
International Conference on Machine Learning (ICML), 2020
arXiv |
site |
code
|
|
Scalable Multi-Task Imitation Learning with Autonomous Improvement
Avi Singh*, Eric Jang, Alexander Irpan, Daniel Kappler, Murtaza
Dalal, Sergey Levine, Mohi Khansari, Chelsea Finn
International Conference on Robotics and Automation (ICRA), 2020.
arXiv |
site |
video
|
|
Visual Reinforcement Learning with Imagined Goals
Ashvin Nair*, Vitchyr H. Pong*, Murtaza
Dalal, Shikhar Bahl, Steven Lin, Sergey Levine
Advances in Neural Information Processing Systems (NeurIPS), 2018
(Spotlight)
arXiv |
site |
code |
blog
|
|
Composable Deep Reinforcement Learning for Robotic Manipulation
Tuomas Haarnoja*,
Vitchyr H. Pong,
Aurick Zhou,
Murtaza Dalal,
Pieter Abbeel,
Sergey Levine
International Conference on Robotics and Automation (ICRA), 2018.
arXiv |
site |
code
|
|
Temporal Difference Models: Model-Free Deep RL for Model-Based Control
Vitchyr H. Pong*,
Shixiang Gu*,
Murtaza Dalal,
Sergey Levine
International Conference on Learning Representations (ICLR), 2018.
arXiv |
code |
blog
|
Modified version of template from here
|
|