Introduction to Reinforcement Learning (2015) • Hacker News Board

Re: Introduction to Reinforcement Learning (2015)

#41

Post by flooo » Sun, Dec 27, 2020, 7:33 PM UTC

jmeister wrote: post #26

patrick_halina wrote: post #25

Earlier quoted context omitted.

RL is a good theoretical solution for personalization: given a user state, select an action that maximizes a long term reward (eg. revenue/engagement.) It’s tricky building the implementations because unlike Go/Chess/Atari it’s hard to simulate humans. So you have to train the agents with batches of data offline (ie. using historic data from the agent’s past actions.) This is challenging because you don’t get as many…

I’ve not kept up with the recent developments in this field - is Vowpal Wabbit widely used now? Any competitors? Or do people build their own in-house systems? Thanks

Vowpal Wabbit is used but many build something in-house into existing rule-based or supervised ml systems

In green fields deployments, Azure personalizer may be a nice place to start looking.

On the academic side, this paper provides an overview https://content.iospress.com/articles/data-science/ds200028

Re: Introduction to Reinforcement Learning (2015)

#42

Post by stevofolife » Sun, Dec 27, 2020, 8:08 PM UTC

bonoboTP wrote: post #10

jsemrau wrote: post #8

Earlier quoted context omitted.

When the first PC with Basic launched in the 80s many people wanted to develop for it. When the iPhone Appstore launched, many people started to build apps in the ecosystem. While it might be it bit too early to compare RL to those advances in technology. I personally feel there is huge potential. I might be wrong though. And I am fine with that.

RL isn't new though, the foundational results are about 25 years old.

No one said "new". You can apply what you said to PC and iPhones. Mainframes and palms existed before them.

Re: Introduction to Reinforcement Learning (2015)

#43

Post by bitL » Mon, Dec 28, 2020, 3:03 PM UTC

cbames89 wrote: post #17

bitL wrote: post #14

Earlier quoted context omitted.

RL needs a supercomputer and its code is usually too fragile - making a trivial mistake anywhere (missing a constant multiplication, swapping the order of two consecutive lines of code etc.) would likely lead to your model never converging even if you got everything else right.

Technical point: Value functions that are a constant multiples of each other result in the same behavior.

Making a constant multiplication mistake somewhere in the code doesn't imply the new value function would be a constant multiply of the optimal one.

Re: Introduction to Reinforcement Learning (2015)

#44

Post by Buttons840 » Mon, Dec 28, 2020, 6:08 PM UTC

dgb23 wrote: post #27

Asking from a layman's perspective: I've read a bit about genetic algorithms or evolutionary computation at some point. Apparently it achieves good results as it can find discrete solutions for complex, well defined problems. Reinforcement learning is something I know even less about. But from what I gathered it is also most successful in well defined problems and systems (such as games). So my question is: How do th…

Genetic algorithms randomly change things and then test to see if they're better. Reinforcement learning does analysis on past observations and then makes deliberate improvements.

Re: Introduction to Reinforcement Learning (2015)

#45

Post by jmeister » Wed, Dec 30, 2020, 3:14 PM UTC

flooo wrote: post #41

jmeister wrote: post #26

Earlier quoted context omitted.

I’ve not kept up with the recent developments in this field - is Vowpal Wabbit widely used now? Any competitors? Or do people build their own in-house systems? Thanks

Vowpal Wabbit is used but many build something in-house into existing rule-based or supervised ml systems In green fields deployments, Azure personalizer may be a nice place to start looking. On the academic side, this paper provides an overview https://content.iospress.com/articles/data-science/ds200028

Thank you, the review looks helpful.