📇
DeepRL
  • CS285: Deep RL Notes
  • RL Fundamentals
  • Policy Gradient
    • Policy Gradient Basics
    • Actor Critic Algorithms
    • Advanced Policy Gradients
  • Value Based Methods
    • Policy and Value Iteration Algorithms
    • DQN and beyond
  • Model-based Methods
    • Model-based Planning and Model-based Predictive Control
    • Model-based Policy Learning
  • Inference, Control, and Inverse RL
    • Latent Models and Variational Inference
    • Control as Inference
    • Inverse Reinforcement Learning
  • Transfer Learning in RL
    • Transfer and Multi-task Learning
    • Paper Reading Notes
  • Coming soon...
    • Offline RL
    • RL from Pixels
Powered by GitBook
On this page

CS285: Deep RL Notes

NextRL Fundamentals

Last updated 4 years ago

For UC Berkeley CS285: Deep Reinforcement Learning, Decision Making, and Control, taught by Professor Sergey Levine.

Official Course Website:

These are my personal notes and wordy explanations on the core topics covered in this course, it’s meant to be a reference and sanity check for myself and for others learning deep RL. I typically write extensively about the most important parts of each lecture, so the notes are not (yet) comprehensive. I highly recommend watching the recorded lectures if you are self-studying for this class, professor Levine is a fantastic lecturer and many student questions that got recorded were also really interesting.

All screenshots/images in these notes credit to CS285 lecture slides. I'll try to keep updating new topics whenever possible, please reach out to me to if you’d like to contribute to writing or beautifying these notes!

Happy Reinforcement Learning! :)

http://rail.eecs.berkeley.edu/deeprlcourse
mandi.zhao@berkeley.edu