Notes and References

Github Repositories

  • RLKIT (fork version)
  • Doodad (fork version)

    • Exercises

  • Project I - DQN Cartpole (RLKIT and stable-baselines3)
  • Project II - DQN Atari Breakout (RLKIT)

    • Readings

  • Reading List

    • My Reading Notes
  • Readings I - DQN (Deep Q-Learning Algorithm)
  • Readings II - GRL (Generalization in Reinforcement Learning)
  • Readings III - IQL (Implicit Q-Learning) (1)

    • References:
    (1) Offline Reinforcement Learning with Implicit Q-Learning

    Tutorial Notes

    Fundamentals of RL
  • RL Summary (1)
  • RL Notes (1)

    • Generalization in RL
  • Meta Reinforcement Learning (2)
  • Generalization in Robotics (My notes from Glen's Generalization in Robotics' class)

    • Others
  • Pytorch Tutorials (3)
  • Docker Tutorial (4)

    • References:
    (1) Lectures of Steven L. Brunton
    (2) Video: Meta Reinforcement Learning (Chelsea Finn)
    (3) Pytorch Tutorials Playlist by Python Engineer
    (4) Docker Complete Course by TechWorld with Nana