Russell Mendonca

CV | Google Scholar | Twitter

I am a PhD candidate in the Robotics Institute at Carnegie Mellon University, advised by Prof. Deepak Pathak, interested in working on problems in machine learning, robotics and computer vision to enable general purpose agents.

Previously, I graduated from UC Berkeley in Electrical Engineering and Computer Science, and worked on reinforcement learning with Prof. Sergey Levine in the Berkeley Artificial Intelligence Lab (BAIR)

You can contact me via email at rmendonc -at- andrew dot cmu dot edu


  Research

I am broadly interested in building generalist agents that can continually improve in capability. My work focuses on data-driven robot learning, including exploration for RL using world models, affordances from human video for manipulation tasks, and continually improving mobile manipulation systems. Here is some of my work (representative papers are highlighted):


Continuously Improving Mobile Manipulation
with Autonomous Real-World RL

Russell Mendonca, Bernadette Bucher, Jiuguang Wang, Deepak Pathak
In submission  

webpage | abstract

sym

Video Diffusion Alignment via Reward Gradients
Mihir Prabhudesai*, Russell Mendonca*, Zheyang Qin*, Katerina Fragkiadaki,
Deepak Pathak
In submission  

webpage | abstract

Adaptive Mobile Manipulation for Articulated
Objects in the Open World

Haoyu Xiong, Russell Mendonca, Kenneth Shaw, Deepak Pathak
In submission  

webpage | pdf | abstract | bibtex |

  @article{xiong2024adaptive,
    title={Adaptive mobile manipulation 
    for articulated objects in the open world},
    author={Xiong, Haoyu and Mendonca, 
    Russell and Shaw, Kenneth and Pathak, Deepak},
    journal={arXiv preprint arXiv:2401.14403},
    year={2024},
  }

OpenX Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration
ICRA 2024  

webpage | pdf | abstract | bibtex |

      @misc{open_x_embodiment_rt_x_2023,
        title={Open {X-E}mbodiment: Robotic
        Learning Datasets and {RT-X} Models},
        author = {Open X-Embodiment Collaboration },
        howpublished  = {\url{https://arxiv.org/abs/2310.08864}},
        year = {2023},
        }
    

Structured World Models from Human Videos
Russell Mendonca*, Shikhar Bahl*, Deepak Pathak
RSS 2023  

webpage | pdf | abstract | bibtex |

  @article{mendonca23swim,
  title={Structured World Models 
  from Human Videos},
  author={Mendonca, Russell and 
  Bahl, Shikhar and Pathak, Deepak},
  journal={RSS},
  year={2023},
}

Affordances from Human Videos as a Versatile
Representation for Robotics

Shikhar Bahl*, Russell Mendonca*, Lili Chen, Unnat Jain,
Deepak Pathak
CVPR 2023

webpage | pdf | abstract | bibtex |

      @article{bahl2023affordances,
      title={Affordances from Human Videos 
      as a Versatile Representation 
      for Robotics},
      author={Bahl, Shikhar and Mendonca, 
      Russell and Chen, Lili and Jain, 
      Unnat and Pathak, Deepak},
      journal={CVPR},
      year={2023}
      }
    
sym

Efficient RL via Disentangled Environment and
Agent Representations

Kevin Gmelin*, Shikhar Bahl*, Russell Mendonca, Deepak Pathak
ICML 2023

webpage | pdf | abstract | bibtex |

      @article{Gmelin2023sear,
      title={Efficient RL via Disentangled 
      Environment and Agent Representations},
      author={Gmelin, Kevin and Bahl, Shikhar
      and Mendonca, Russell and Pathak, Deepak},
      journal={ICML},
      year={2023}
      }
    

ALAN : Autonomously Exploring Robotic Agents in the Real World
Russell Mendonca, Shikhar Bahl, Deepak Pathak
ICRA 2023

webpage | pdf | abstract | bibtex |

  @article{mendonca2023alan,
    author = {Mendonca, Russell and
    Bahl, Shikhar and
    Pathak, Deepak},
    title  = {ALAN : Autonomously Exploring 
    Robotic Agents in the Real World},
    journal= {ICRA},
    year   = {2023}
  }
sym

Discovering and Achieving Goals via World Models
Russell Mendonca*, Oleh Rybkin*,
Kostas Daniilidis, Danijar Hafner, Deepak Pathak
NeurIPS 2021

webpage | pdf | abstract | bibtex | code | benchmark | talk video

  @inproceedings{mendonca2021lexa,
  Author = {Mendonca, Russell and
  Rybkin, Oleh and Daniilidis, Kostas and
  Hafner, Danijar and Pathak, Deepak},
  Title = {Discovering and Achieving
  Goals via World Models},
  Booktitle = {NeurIPS},
  Year = {2021}
  }
  
sym

Guided Meta-Policy Search
Russell Mendonca, Abhishek Gupta, Rosen Kralev,
Pieter Abbeel, Sergey Levine, Chelsea Finn
NeurIPS 2019 (spotlight)

webpage | pdf | abstract | bibtex | code |

    @inproceedings{mendonca2019gmps,
    Author = {Mendonca, Russell and
    Gupta, Abhishek and Kralev, Rosen and
    Abbeel, Pieter and Levine, 
    Sergey and Finn, Chelsea},
    Title = {Guided Meta-Policy Search},
    Booktitle = {NeurIPS},
    Year = {2019}
    }
    
sym

Meta-Reinforcement Learning of Structured Exploration Strategies
Abhishek Gupta, Russell Mendonca, YuXuan Liu,
Pieter Abbeel, Sergey Levine
NeurIPS 2018 (spotlight)

slides | pdf | abstract | bibtex | code |

      @inproceedings{gupta2018maesn,
      Author = {Gupta, Abhishek and 
      Mendonca, Russell and Liu, YuXuan and
      Abbeel, Pieter and Levine, Sergey},
      Title = {Meta-Reinforcement Learning 
      of Structured Exploration Strategies},
      Booktitle = {NeurIPS},
      Year = {2018}
      }
      
sym

Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
Russell Mendonca *, Xinyang Geng *, Chelsea Finn, Sergey Levine
Inductive biases, invariances and generalization in RL
ICML Workshop , 2020

pdf | abstract | bibtex |

          @misc{mendonca2020metareinforcement,
            title={Meta-Reinforcement Learning 
            Robust to Distributional Shift 
            via Model Identification 
            and Experience Relabeling}, 
            author={Russell Mendonca and Xinyang 
            Geng and Chelsea Finn and Sergey Levine},
            year={2020},
            eprint={2006.07178},
            archivePrefix={arXiv},
            primaryClass={cs.LG}
      }

        


Modified version of template from here