Applications in RL Worskshop

Baldy 110, March 9, 2020


The goal of reinforcement learning is to train agents that interact with their environment to solve complex tasks, with real-world applications ranging from robotics, self-driving cars, real-time bidding and more. From one angle we need to develop algorithms to solve tasks, but from another we need to build an RL environment that will mimic real-world problems. As of now, there are a number of professional developed RL environments that researchers can use to develop and compare RL algorithms. The main purpose of this workshop is to review the most common RL toolkits.

Workshop Outline:

  1. Intro by Alina Vereshchaka
  2. Defining & Solving Grid-world Environment by Utkarsh Behre
  3. Utkarsh_Behre
    Utkarsh Behre
  4. Open AI Gym by Charan Nama Arunkumar (ipynb)
  5. Charan_Nama_Arunkumar
    Charan Nama Arunkumar
  6. Google Research Football by Vaibhav Prakash Chhajed (pdf)
  7. Vaibhav_Prakash_Chhajed
    Vaibhav Prakash Chhajed
  8. Multi-agent RL by Alina Vereshchaka (pdf)
  9. Alina_Vereshchaka
    Alina Vereshchaka
  10. DeepRacer AWS by Steven Korzelius
  11. Steven_Korzelius
    Steven Korzelius
  12. Pizza & Networkig

Thank you to everyone who took part in the event!

Reinforcement Learning Class Spring 2020

Photographer: Xingtong Li