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 Igor Mordatch

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning


Nov 04, 2021
Wenlong Huang, Igor Mordatch, Pieter Abbeel, Deepak Pathak

* Website at https://huangwl18.github.io/geometry-dex 

  Access Paper or Ask Questions

Unsupervised Learning of Compositional Energy Concepts


Nov 04, 2021
Yilun Du, Shuang Li, Yash Sharma, Joshua B. Tenenbaum, Igor Mordatch

* NeurIPS 2021, website and code at https://energy-based-model.github.io/comet/ 

  Access Paper or Ask Questions

The Neural MMO Platform for Massively Multiagent Research


Oct 14, 2021
Joseph Suarez, Yilun Du, Clare Zhu, Igor Mordatch, Phillip Isola


  Access Paper or Ask Questions

Implicit Behavioral Cloning


Sep 01, 2021
Pete Florence, Corey Lynch, Andy Zeng, Oscar Ramirez, Ayzaan Wahid, Laura Downs, Adrian Wong, Johnny Lee, Igor Mordatch, Jonathan Tompson


  Access Paper or Ask Questions

Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot


Jul 14, 2021
Joel Z. Leibo, Edgar Duéñez-Guzmán, Alexander Sasha Vezhnevets, John P. Agapiou, Peter Sunehag, Raphael Koster, Jayd Matyas, Charles Beattie, Igor Mordatch, Thore Graepel

* In International Conference on Machine Learning 2021 (pp. 6187-6199). PMLR 
* Accepted to ICML 2021 and presented as a long talk; 33 pages; 9 figures 

  Access Paper or Ask Questions

Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation


Jun 24, 2021
C. Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, Olivier Bachem

* 9 pages + 12 pages of appendices and references. In submission at NeurIPS 2021 Datasets and Benchmarks Track 

  Access Paper or Ask Questions

Model-Based Reinforcement Learning via Latent-Space Collocation


Jun 24, 2021
Oleh Rybkin, Chuning Zhu, Anusha Nagabandi, Kostas Daniilidis, Igor Mordatch, Sergey Levine

* International Conference on Machine Learning (ICML), 2021. Videos and code at https://orybkin.github.io/latco/ 

  Access Paper or Ask Questions

Decision Transformer: Reinforcement Learning via Sequence Modeling


Jun 24, 2021
Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch

* First two authors contributed equally. Last two authors advised equally 

  Access Paper or Ask Questions

Pretrained Transformers as Universal Computation Engines


Mar 09, 2021
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch


  Access Paper or Ask Questions

Reset-Free Lifelong Learning with Skill-Space Planning


Jan 01, 2021
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

* Website link: https://sites.google.com/berkeley.edu/reset-free-lifelong-learning 

  Access Paper or Ask Questions

Improved Contrastive Divergence Training of Energy Based Models


Dec 17, 2020
Yilun Du, Shuang Li, Joshua Tenenbaum, Igor Mordatch

* Project webpage at https://energy-based-model.github.io/improved-contrastive-divergence 

  Access Paper or Ask Questions

Energy-Based Models for Continual Learning


Nov 24, 2020
Shuang Li, Yilun Du, Gido M. van de Ven, Antonio Torralba, Igor Mordatch


  Access Paper or Ask Questions

Rearrangement: A Challenge for Embodied AI


Nov 03, 2020
Dhruv Batra, Angel X. Chang, Sonia Chernova, Andrew J. Davison, Jia Deng, Vladlen Koltun, Sergey Levine, Jitendra Malik, Igor Mordatch, Roozbeh Mottaghi, Manolis Savva, Hao Su

* Authors are listed in alphabetical order 

  Access Paper or Ask Questions

$γ$-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction


Oct 27, 2020
Michael Janner, Igor Mordatch, Sergey Levine

* NeurIPS 2020. Project page at: https://people.eecs.berkeley.edu/~janner/gamma-models/ 

  Access Paper or Ask Questions

One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control


Jul 09, 2020
Wenlong Huang, Igor Mordatch, Deepak Pathak

* Accepted at ICML 2020. Videos and code at https://huangwl18.github.io/modular-rl/ 

  Access Paper or Ask Questions

A Game Theoretic Framework for Model Based Reinforcement Learning


Apr 16, 2020
Aravind Rajeswaran, Igor Mordatch, Vikash Kumar

* Project webpage: https://sites.google.com/view/mbrl-game 

  Access Paper or Ask Questions

Compositional Visual Generation and Inference with Energy Based Models


Apr 13, 2020
Yilun Du, Shuang Li, Igor Mordatch

* Website at https://energy-based-model.github.io/compositional-generation-inference/ 

  Access Paper or Ask Questions

Adaptive Online Planning for Continual Lifelong Learning


Dec 03, 2019
Kevin Lu, Igor Mordatch, Pieter Abbeel

* NeurIPS Deep RL 2019 

  Access Paper or Ask Questions

Emergent Tool Use From Multi-Agent Autocurricula


Sep 17, 2019
Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew, Igor Mordatch


  Access Paper or Ask Questions

Model Based Planning with Energy Based Models


Sep 15, 2019
Yilun Du, Toru Lin, Igor Mordatch

* CoRL 2019 

  Access Paper or Ask Questions

Implicit Generation and Generalization in Energy-Based Models


Mar 20, 2019
Yilun Du, Igor Mordatch


  Access Paper or Ask Questions

Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents


Mar 02, 2019
Joseph Suarez, Yilun Du, Phillip Isola, Igor Mordatch


  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

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control


Jan 28, 2019
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch

* The first two authors contributed equally. Accepted at ICLR 2019. Supplementary videos available at: https://sites.google.com/view/polo-mpc 

  Access Paper or Ask Questions

Concept Learning with Energy-Based Models


Nov 06, 2018
Igor Mordatch


  Access Paper or Ask Questions

Learning with Opponent-Learning Awareness


Sep 19, 2018
Jakob N. Foerster, Richard Y. Chen, Maruan Al-Shedivat, Shimon Whiteson, Pieter Abbeel, Igor Mordatch


  Access Paper or Ask Questions