Wah Loon Keng

-inactive-

[Wah Loon Keng @kengzwl]

Expanded benchmark and wall of RL GIFs over at SLM Lab
https://t.co/MNUBFjtu9d

[Wah Loon Keng @kengzwl]

@GoogleStadia I’m on chromecast ultra with wired connection, have been playing other games at 4K. I saw some people having the same issue; anyway it got better a few hours later, maybe the server was strained?

[Wah Loon Keng @kengzwl]

@GoogleStadia Hi just opened the game. Why is it not 4K, and how do we get 4K? I even set the graphics to “visual” and restarted.

[Wah Loon Keng @kengzwl]

@lgraesser3 @filar We also keep a list of RL environments if you need some reference https://t.co/eTwdTaQ3jA

[Aleksandra Faust @AleksandraFaust]

What's the best way to learn deep RL? Write a book, of course! Congratulations @lgraesser3! Honored to work with you!

Foundations of Deep Reinforcement Learning: Theory and Practice in Python (Addison-Wesley Data & Analytics Series) https://t.co/P8AGVFCH0D

[Wah Loon Keng @kengzwl]

@lgraesser3 and I co-wrote a book "Foundations of Deep Reinforcement Learning" and it's coming out next week!

For now, you can preorder it at a discount (thanks to Black Friday) at the Pearson website:

https://t.co/IRr4NUb1YR

[Wah Loon Keng @kengzwl]

Full Atari and Roboschool benchmark results available in SLM Lab: https://t.co/onDxG3YAcy

[Tomasz Łakomy @tlakomy]

Is this Docker?

[Rhys Thomas @DrGetafix]

Schrödinger's cat, demonstrating here that cats are both waves and particles. https://t.co/ZnDFMjBrzl

[Matthew Honnibal @honnibal]

Extremely strong flex here.

[Lilian Weng @lilianweng]

Gradient descent is not the only option when optimizing model parameters. Evolution strategies can help too. Check out my new post if you are interested in how CMA-ES works or the way ES is used in deep RL: https://t.co/GBnSWx174x

[Wah Loon Keng @kengzwl]

@tkasasagi Pro is nice. I remap to make (Cmd, alt, ",?) into (left, right, up down). Up down are layered and so triggered only by the fn key. Deliberately put up down together and left right together so they're easy to home in. U can use this to remap:
https://t.co/LPBGMSPmhw

[Hacker News Bot @newsycombinator]

Alan Turing to be the face of new £50 note https://t.co/DL5oPP6zBr

[Hacker News Bot @newsycombinator]

You Are Not Your Code (2012) https://t.co/hjhP26VtGY

[Wah Loon Keng @kengzwl]

@thekevinwang

[Hacker News Bot @newsycombinator]

A Simulated Enigma Machine https://t.co/1cHRb4a9QW

[Wah Loon Keng @kengzwl]

Me with back-pain after climbing be walking like this

[Wah Loon Keng @kengzwl]

A collection of Deep RL resources https://t.co/A3s1eR1RIL

[Wah Loon Keng @kengzwl]

Implemented Soft Actor-Critic in SLM Lab, and got it to work for discrete environments with minimal tweak. Brief details: https://t.co/HIf0KwvECe

graphs: LunarLander(discrete), Walker2d (continuous)

[Wah Loon Keng @kengzwl]

Multi-arm bandit
(from very old Japanese Yokai Manga)