Marc Rigter

Welcome to my personal website!

I’m currently a postdoc at the Applied AI Lab at the Oxford Robotics Institute (ORI) at the University of Oxford. My research focuses on generative “world” models and model-based reinforcement learning.

I recently completed my PhD in Information Engineering at the GOALS Group also at the ORI. The focus of my PhD research was risk and robustness in reinforcement learning.

Please feel free to reach out if you would like to chat about anything!

Photo Collections

New Zealand / Aotearoa

United Kingdom

United States

Australia

Europe

South East Asia

Wildlife

Selected Publications

ICLR

Reward-free curricula for training robust world models

Marc Rigter , Minqi Jiang , and Ingmar Posner

International Conference on Learning Representations, 2024

Bib PDF Code

@article{rigter2024reward,
  title = {Reward-free curricula for training robust world models},
  author = {Rigter, Marc and Jiang, Minqi and Posner, Ingmar},
  journal = {International Conference on Learning Representations},
  year = {2024},
}

Preprint

World models via policy-guided trajectory diffusion

Marc Rigter , Jun Yamada , and Ingmar Posner

arXiv preprint arXiv:2312.08533, 2023

Bib PDF Code

@article{rigter2023world,
  title = {World models via policy-guided trajectory diffusion},
  author = {Rigter, Marc and Yamada, Jun and Posner, Ingmar},
  journal = {arXiv preprint arXiv:2312.08533},
  year = {2023},
}

NeurIPS

One risk to rule them all: A risk-sensitive perspective on model-based offline reinforcement learning

Marc Rigter , Bruno Lacerda , and Nick Hawes

Advances in Neural Information Processing Systems, 2023

Bib PDF Code

@article{rigter2023one,
  title = {One risk to rule them all: {A} risk-sensitive perspective on model-based offline reinforcement learning},
  author = {Rigter, Marc and Lacerda, Bruno and Hawes, Nick},
  journal = {Advances in Neural Information Processing Systems},
  year = {2023},
}

NeurIPS

RAMBO-RL: Robust adversarial model-based offline reinforcement learning

Marc Rigter , Bruno Lacerda , and Nick Hawes

Advances in Neural Information Processing Systems, 2022

Bib PDF Code

@article{rigter2022rambo,
  title = {{RAMBO-RL}: Robust adversarial model-based offline reinforcement learning},
  author = {Rigter, Marc and Lacerda, Bruno and Hawes, Nick},
  journal = {Advances in Neural Information Processing Systems},
  year = {2022},
}

AAAI

Optimal admission control for multiclass queues with time-varying arrival rates via state abstraction

Marc Rigter , Danial Dervovic , Parisa Hassanzadeh , and 3 more authors

AAAI Conference on Artificial Intelligence, 2022

Bib PDF

@article{rigter2022optimal,
  title = {Optimal admission control for multiclass queues with time-varying arrival rates via state abstraction},
  author = {Rigter, Marc and Dervovic, Danial and Hassanzadeh, Parisa and Long, Jason and Zehtabi, Parisa and Magazzeni, Daniele},
  journal = {AAAI Conference on Artificial Intelligence},
  year = {2022},
}

ICAPS

Planning for risk-aversion and expected value in MDPs

Marc Rigter , Paul Duckworth , Bruno Lacerda , and 1 more author

International Conference on Automated Planning and Scheduling, 2022

Bib PDF Code

@article{rigter2022planning,
  title = {Planning for risk-aversion and expected value in MDPs},
  author = {Rigter, Marc and Duckworth, Paul and Lacerda, Bruno and Hawes, Nick},
  journal = {International Conference on Automated Planning and Scheduling},
  year = {2022},
}

NeurIPS

Risk-averse Bayes-adaptive reinforcement learning

Marc Rigter , Bruno Lacerda , and Nick Hawes

Advances in Neural Information Processing Systems, 2021

Bib PDF

@article{rigter2021risk,
  title = {Risk-averse {B}ayes-adaptive reinforcement learning},
  author = {Rigter, Marc and Lacerda, Bruno and Hawes, Nick},
  journal = {Advances in Neural Information Processing Systems},
  year = {2021},
}

AAAI

Minimax regret optimisation for robust planning in uncertain Markov decision processes

Marc Rigter , Bruno Lacerda , and Nick Hawes

AAAI Conference on Artificial Intelligence, 2021

Bib PDF

@article{rigter2021minimax,
  title = {Minimax regret optimisation for robust planning in uncertain Markov decision processes},
  author = {Rigter, Marc and Lacerda, Bruno and Hawes, Nick},
  journal = {AAAI Conference on Artificial Intelligence},
  year = {2021},
}

RAL

A framework for learning from demonstration with minimal human effort

Marc Rigter , Bruno Lacerda , and Nick Hawes

IEEE Robotics and Automation Letters, 2020

Bib PDF

@article{rigter2020framework,
  title = {A framework for learning from demonstration with minimal human effort},
  author = {Rigter, Marc and Lacerda, Bruno and Hawes, Nick},
  journal = {IEEE Robotics and Automation Letters},
  year = {2020},
}