Skip to content
@agent-lab

Agent Lab @ University of Manchester

Welcome to Agent Lab

Taking actions intelligently is all we study

We are interested in research on agent taking actions through Deep Learning, with a particular focus on machine learning techniques such as deep reinforcement learning and learning from demonstration. We are applying these methods to problems in video games, robotics and multi-agent systems.

On-going projects:

  • Policy gradients in large-scale training;
  • Transformers and generative models for decision-making tasks;
  • Online learning from interactions and demonstrations.

Code of conduct

  1. Clearly state the purpose and mission of your PhD study
  2. Set specific goals for your research
  3. About your projects: first complete, then perfect
  4. Strive harder than anyone else for your research
  5. Always keep a passionate desire for your research
  6. Always be creative in your research
  7. No falsification, fabrication and plagiarism at any time
  8. Be kind and sincere, remain humble
  9. Appreciate life and do good deeds
  10. Deal with research first, then deal with emotions

Popular repositories Loading

  1. smacv2 smacv2 Public

    Forked from oxwhirl/smacv2

    Python 3

  2. diffusion-integer-programming diffusion-integer-programming Public

    Python 2

  3. DeepMimic_diffusion_mujoco DeepMimic_diffusion_mujoco Public

    Forked from mingfeisun/DeepMimic_mujoco

    DeepMimic Mujoco version; Python only; No Bullet, No C++

    Jupyter Notebook 1 1

  4. .github .github Public

  5. agent-lab.github.io agent-lab.github.io Public

  6. attention-learn-to-route attention-learn-to-route Public

    Forked from wouterkool/attention-learn-to-route

    Attention based model for learning to solve different routing problems

    Jupyter Notebook

Repositories

Showing 7 of 7 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…