Profile picture
Deep Learning Indaba @DeepIndaba
, 10 tweets, 5 min read Read on Twitter
Dave Silver tells us his principles of Deep RL. 1. Evaluation drives progress. #DLIndaba2018
Principles of RL number 2: Scalability determines success.
principles of RL number 3: generality future-proofs our algorithms. #DLIndaba2018
Principles of RL number 4: Trust in the agent's experience. #DLIndaba2018
Principles of RL number 5: State is subjective. #DLIndaba2018
Principles of RL number 6: Control the stream. #DLIndaba2018
Principles of RL number 7: Value functions model the world. #DLIndaba2018
Principles of RL number 8: Planning is learning from imagined experience. #DLIndaba2018
Principles of RL number 9: Empower the function approximator. #DLIndaba2018
Principles of RL number 10: learn to learn. #DLIndaba2018
Missing some Tweet in this thread?
You can try to force a refresh.

Like this thread? Get email updates or save it to PDF!

Subscribe to Deep Learning Indaba
Profile picture

Get real-time email alerts when new unrolls are available from this author!

This content may be removed anytime!

Twitter may remove this content at anytime, convert it as a PDF, save and print for later use!

Try unrolling a thread yourself!

how to unroll video

1) Follow Thread Reader App on Twitter so you can easily mention us!

2) Go to a Twitter thread (series of Tweets by the same owner) and mention us with a keyword "unroll" @threadreaderapp unroll

You can practice here first or read more on our help page!

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member and get exclusive features!

Premium member ($30.00/year)

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!