About

The UT Robot Learning Reading Group meets weekly to discuss the latest papers in robot learning. This group is run by the Robot Perception and Learning Lab at UT Austin. This group is accessible to all UT Austin students.

Logistics

Each week, we meet for one hour on Zoom to discuss one paper in depth. One student will lead each meeting with a presentation on the paper.

We follow the latest papers in robotics and embodied AI, spanning topics such as computer vision, reinforcement learning, neuro-symbolic AI, and control. We survey papers from a broad set of conferences, including (but not limited to) CoRL, RSS, and CVPR.

How to Join

This group is currently maintained by Soroush Nasiriany. If you are interested in joining the reading group: please contact him at {his_first_name}@cs.utexas.edu to be added to the internal mailing list.

Reading list

Spring 2021

[4/8/21]
Unsupervised Monocular Depth Learning in Dynamic Scenes
Hanhan Li, Ariel Gordon, Hang Zhao, Vincent Casser, Anelia Angelova
CoRL 2020
Presenter: Amanda Adkins
[Paper] [Slides]

[4/1/21]
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification
Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov
arXiv 2021
Presenter: Dian Chen
[Paper] [Project] [Slides]

[3/25/21]
Point Transformer
Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun
arXiv 2020
Presenter: Zhenyu Jiang
[Paper] [Slides]

[3/11/21]
Stein Variational Model Predictive Control
Alexander Lambert, Adam Fishman, Dieter Fox, Byron Boots, Fabio Ramos
CoRL 2020
Presenter: Mingyo Seo
[Paper] [Video] [Slides]

[3/4/21]
Semantic Visual Navigation by Watching YouTube Videos
Matthew Chang, Arjun Gupta, Saurabh Gupta
NeurIPS 2020
Presenter: Jerry Lin
[Paper] [Project] [Slides]

[2/25/21]
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
Avi Singh*, Huihan Liu*, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine
ICLR 2021
Presenter: Mohan Kumar Sriram
[Paper] [Project] [Slides]

[2/11/21]
Constructing Symbolic Representations for High-Level Planning
George Konidaris, Leslie Pack Kaelbling, Tomás Lozano-Pérez
AAAI 2014
Presenter: Yifeng Zhu
[Paper] [Video] [Slides]

[2/4/21]
Where2Act: From Pixels to Actions for Articulated 3D Objects
Kaichun Mo, Leonidas Guibas, Mustafa Mukadam, Abhinav Gupta, Shubham Tulsiani
arXiv 2021
Presenter: Zhenyu Jiang
[Paper] [Project] [Slides]

[1/28/21]
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Kanishka Rao, Chris Harris, Alex Irpan, Sergey Levine, Julian Ibarz, Mohi Khansari
CVPR 2020
Presenter: Soroush Nasiriany
[Paper] [Video] [Slides]

Fall 2020

[12/3/20]
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall*, Pratul P. Srinivasan*, Matthew Tancik*, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng
ECCV 2020
Presenter: Zhenyu Jiang
[Paper] [Project] [Slides]

[11/19/20]
Learning Invariant Representations for Reinforcement Learning without Reconstruction
Amy Zhang*, Rowan McAllister*, Roberto Calandra, Yarin Gal, Sergey Levine
ICLR 2021
Presenter: Jerry Lin
[Paper] [Project]

[11/12/20]
Accelerating Reinforcement Learning with Learned Skill Priors
Karl Pertsch, Youngwoon Lee, Joseph J. Lim
CoRL 2020
Presenter: Soroush Nasiriany
[Paper] [Project] [Slides]

[11/5/20]
Learning an Optimal Sampling Distribution for Efficient Motion Planning
Richard Cheng, Krishna Shankar, Joel W. Burdick
IROS 2020
Presenter: Mingyo Seo
[Paper] [Slides]