Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations


Jul 27, 2022
Kuang-Huei Lee, Ofir Nachum, Tingnan Zhang, Sergio Guadarrama, Jie Tan, Wenhao Yu

* To appear at IROS 2022. The supplementary video is available at https://kuanghuei.github.io/piars 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Semantics-Aware Locomotion Skills from Human Demonstration


Jun 27, 2022
Yuxiang Yang, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Robustness of Safe Reinforcement Learning under Observational Perturbations


May 29, 2022
Zuxin Liu, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li, Ding Zhao

* 27 pages, 3 figures, 3 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-objective evolution for Generalizable Policy Gradient Algorithms


Apr 08, 2022
Juan Jose Garau-Luis, Yingjie Miao, John D. Co-Reyes, Aaron Parisi, Jie Tan, Esteban Real, Aleksandra Faust

* 23 pages, 12 figures, 10 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Safe Reinforcement Learning for Legged Locomotion


Mar 05, 2022
Tsung-Yen Yang, Tingnan Zhang, Linda Luu, Sehoon Ha, Jie Tan, Wenhao Yu

* Video is included in the submission and the project website: https://sites.google.com/view/saferlleggedlocomotion/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance


Dec 07, 2021
Michael Luo, Ashwin Balakrishna, Brijen Thananjeyan, Suraj Nair, Julian Ibarz, Jie Tan, Chelsea Finn, Ion Stoica, Ken Goldberg

* Workshop on Safe and Robust Control of Uncertain Systems at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recovery


Nov 29, 2021
Yan Du, Qiuhua Huang, Renke Huang, Tianzhixi Yin, Jie Tan, Wenhao Yu, Xinya Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World


Oct 11, 2021
Laura Smith, J. Chase Kew, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine

* Project website: https://sites.google.com/berkeley.edu/fine-tuning-locomotion 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning to Navigate Sidewalks in Outdoor Environments


Sep 12, 2021
Maks Sorokin, Jie Tan, C. Karen Liu, Sehoon Ha

* Submitted to IEEE Robotics and Automation Letters (RA-L) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Disentangled Motif-aware Graph Learning for Phrase Grounding


Apr 13, 2021
Zongshen Mu, Siliang Tang, Jie Tan, Qiang Yu, Yueting Zhuang

* 10 pages, 6 figures, AAAI 2021 conference 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>