Reinforcement Learning

Here will be all important resources and content that I found useful while learning Reinforcement Learning.

Topics of Interest

• Continual Learning
• Learning in Multi Agent Systems
• Multi Goal Reinforcement Learning
• Application
  • Robotics
  • Healthcare
  • Finance

Currently Doing

• Go through research institutes section
• Practice
  • OpenAI Gym Leaderboard
  • finish ConnectX
  • AWS DeepRacer League
  • GoCoder
• Learn Control Theory
  • Control Boot Camp
  • Data Driven Control with Machine Learning
  • Intro to Data Intensive Engineering
• NeurIPS Talk
  • Talks about Reproducibility, Re-usability & Robustness
• RLDM Conference 2022
• Stanford General Game Playing
• Course - CS234 Stanford and Seminar
• Book - Intro to RL
• Workshop by IAS
• Article on Why RL might not work
• Papers to read
• CMU Brain Seminar
• An Introduction to Universal AI | book
• Deep Reinforcement Learning
  • Self-Play (LessWrong)
  • Foundations of RL | 6 Lectures by Pieter Abbeel
  • Practical Deep RL
  • Spinning Up | OpenAI
  • Deep RL UC Berkeley and Practical RL
  • Awesome Deep RL
  • Reproducing Deep RL

Readings

• Simulacra as Conscious Exotica
• Distributional Reinforcement Learning
• Definition of Continual Reinforcement Learning
• Social Path to Human like AI
• Emergent tool use from multi agent interaction
• Learning Policy representations in multi-agent systems
• Third Person Imitation Learning
• Learning to Model other minds
• Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research
• Reptile: A scalable meta-learning algorithm
• AdaRL
• Learning to Teach in Cooperative Multiagent Reinforcement Learning

People and Groups

• Peter Abbeel
• Maria-Florina Balcan
• Auke Jan | BioRob
• Leila Wehbe
• Computation and Cognition Lab
• Learning and Dynamical Systems Group
• ETH AI Center
• EPFL AI
• MIT CSAIL
• Stanford Research Groups

1. Richard Sutton's Group (University of Alberta)
2. Emma Brunskill's Lab (Stanford University): RL with few samples
3. Shimon Whiteson's Lab (University of Oxford)
4. Doina Precup's Lab (McGill University): fundamental RL
5. Jan Peters' Group (TU Darmstadt): site
6. Frank Hutter's Lab (University of Freiburg): site
7. Jürgen Schmidhuber's Group (IDSIA, Switzerland)