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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Aviv Tamar

Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization


Mar 20, 2021
Carmel Rabinovitz, Niko Grupen, Aviv Tamar

* Accepted to ICRA 2021, code can be found at https://github.com/carmelrabinov/cdr 

  Access Paper or Ask Questions

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder


Dec 24, 2020
Tal Daniel, Aviv Tamar

* Code and additional information is available on the project website - https://taldatech.github.io/soft-intro-vae-web 

  Access Paper or Ask Questions

Online Safety Assurance for Deep Reinforcement Learning


Oct 07, 2020
Noga H. Rotman, Michael Schapira, Aviv Tamar

* 8 pages, to appear in The 19th ACM Workshop on Hot Topics in Networks (HotNets 2020) 

  Access Paper or Ask Questions

Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores


Sep 20, 2020
Tzvika Geft, Aviv Tamar, Ken Goldberg, Dan Halperin

* Presented at the 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE) 

  Access Paper or Ask Questions

Offline Meta Reinforcement Learning


Aug 06, 2020
Ron Dorfman, Aviv Tamar


  Access Paper or Ask Questions

Hallucinative Topological Memory for Zero-Shot Visual Planning


Feb 27, 2020
Kara Liu, Thanard Kurutach, Christine Tung, Pieter Abbeel, Aviv Tamar


  Access Paper or Ask Questions

Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learning


Feb 27, 2020
Tom Jurgenson, Or Avner, Edward Groshev, Aviv Tamar

* 8 pages, 10 figures. arXiv admin note: text overlap with arXiv:1906.05329 

  Access Paper or Ask Questions

Deep Residual Flow for Novelty Detection


Jan 15, 2020
Ev Zisselman, Aviv Tamar


  Access Paper or Ask Questions

Deep Variational Semi-Supervised Novelty Detection


Nov 12, 2019
Tal Daniel, Thanard Kurutach, Aviv Tamar


  Access Paper or Ask Questions

Bayesian Relational Memory for Semantic Visual Navigation


Sep 10, 2019
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian

* Accepted at ICCV 2019 

  Access Paper or Ask Questions

Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and Optimization


Jun 12, 2019
Tom Jurgenson, Edward Groshev, Aviv Tamar

* 15 pages (8 main), 2 figures, 4 tables 

  Access Paper or Ask Questions

Harnessing Reinforcement Learning for Neural Motion Planning


Jun 01, 2019
Tom Jurgenson, Aviv Tamar

* 13 pages (all), 8 pages (main sections), 6 figures, 4 tables, accepted to rss2019 

  Access Paper or Ask Questions

Learning Robotic Manipulation through Visual Planning and Acting


May 11, 2019
Angelina Wang, Thanard Kurutach, Kara Liu, Pieter Abbeel, Aviv Tamar

* RSS 2019. Website at https://sites.google.com/berkeley.edu/vpa/home 

  Access Paper or Ask Questions

Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly


Mar 20, 2019
Jianlan Luo, Eugen Solowjow, Chengtao Wen, Juan Aparicio Ojea, Alice M. Agogino, Aviv Tamar, Pieter Abbeel

* ICRA 2019. More video results at https://sites.google.com/berkeley.edu/rl-robotic-assembly/home 

  Access Paper or Ask Questions

Domain Randomization for Active Pose Estimation


Mar 10, 2019
Xinyi Ren, Jianlan Luo, Eugen Solowjow, Juan Aparicio Ojea, Abhishek Gupta, Aviv Tamar, Pieter Abbeel

* Accepted at International Conference on Robotics and Automation (ICRA) 2019 

  Access Paper or Ask Questions

Multi Agent Reinforcement Learning with Multi-Step Generative Models


Jan 29, 2019
Orr Krupnik, Igor Mordatch, Aviv Tamar


  Access Paper or Ask Questions

Model-Ensemble Trust-Region Policy Optimization


Oct 05, 2018
Thanard Kurutach, Ignasi Clavera, Yan Duan, Aviv Tamar, Pieter Abbeel


  Access Paper or Ask Questions

Safe Policy Learning from Observations


Sep 28, 2018
Elad Sarafian, Aviv Tamar, Sarit Kraus


  Access Paper or Ask Questions

Learning and Planning with a Semantic Model


Sep 28, 2018
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian

* submitted to ICLR 2019 

  Access Paper or Ask Questions

Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN


Aug 06, 2018
Dror Freirich, Ron Meir, Aviv Tamar


  Access Paper or Ask Questions

Learning Generalized Reactive Policies using Deep Neural Networks


Jul 25, 2018
Edward Groshev, Maxwell Goldstein, Aviv Tamar, Siddharth Srivastava, Pieter Abbeel


  Access Paper or Ask Questions

Learning Robotic Assembly from CAD


Jul 24, 2018
Garrett Thomas, Melissa Chien, Aviv Tamar, Juan Aparicio Ojea, Pieter Abbeel

* In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 2018 

  Access Paper or Ask Questions

Learning Plannable Representations with Causal InfoGAN


Jul 24, 2018
Thanard Kurutach, Aviv Tamar, Ge Yang, Stuart Russell, Pieter Abbeel

* ICML / IJCAI / AAMAS 2018 Workshop on Planning and Learning (PAL-18) 

  Access Paper or Ask Questions

Safer Classification by Synthesis


Jul 23, 2018
William Wang, Angelina Wang, Aviv Tamar, Xi Chen, Pieter Abbeel


  Access Paper or Ask Questions

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments


Jan 16, 2018
Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch


  Access Paper or Ask Questions

Situationally Aware Options


Nov 20, 2017
Daniel J. Mankowitz, Aviv Tamar, Shie Mannor

* arXiv admin note: substantial text overlap with arXiv:1610.02847 

  Access Paper or Ask Questions

A Machine Learning Approach to Routing


Nov 11, 2017
Asaf Valadarsky, Michael Schapira, Dafna Shahaf, Aviv Tamar


  Access Paper or Ask Questions

Shallow Updates for Deep Reinforcement Learning


Nov 02, 2017
Nir Levine, Tom Zahavy, Daniel J. Mankowitz, Aviv Tamar, Shie Mannor


  Access Paper or Ask Questions

Constrained Policy Optimization


May 30, 2017
Joshua Achiam, David Held, Aviv Tamar, Pieter Abbeel

* Accepted to ICML 2017 

  Access Paper or Ask Questions

Learning from the Hindsight Plan -- Episodic MPC Improvement


Mar 20, 2017
Aviv Tamar, Garrett Thomas, Tianhao Zhang, Sergey Levine, Pieter Abbeel

* Additional experiments for neural network generalization and for varying the planning horizon. Paper accepted to ICRA 2017 

  Access Paper or Ask Questions