Real-World Reinforcement Learning - Watch on Demand

MichaelG
Community Manager
Community Manager
1 min read 2 1 1,231

Reinforcement Learning (RL) is a computational approach to learning from action: an agent will interact with its environment, learn from it, perform actions, and receive rewards as feedback for these actions.

Important progress in the field was recently made in academia, from AlphaStar to OpenAI Dexterity - mainly based on video games. However, since RL provides solutions to sequential decision-making problems, more and more industries are starting to use it.

@simonini_thomas (Research Scientist at Dataiku) discussed the current state of the industry and presented some of the latest applications of Reinforcement Learning in business.

Couldn’t make it to the event? Here you can catch up on the talk with the edited video on demand: 

 

Do you have a follow up question? What's your previous experience with Reinforcement Learning? Have you taken a go at the Conundrum on the topic yet? Comment below!

Labels

?
1 Comment
simonini_thomas
Dataiker Alumni

Hi - thanks to everyone who attended the event.

Here are a few links and useful resources for those of you who want to learn more about the area!

A talk on how Zynga uses RL to time their push notifications and beyond.

EasyJet’s Pedro Alves describes their experience and work with RL including discussions of the challenges and the huge potential of this approach.

Here’s a github of the RLTrader mentioned in the talk - if you want to start to learn more about how that came to be there is a Medium article for you to check out!

And of course a great place to start is the RL Resources article right here on community - as well as the Conundrum where we task you with building your very own wall-jump agent! Don’t worry it’s a very comprehensive challenge with guides and tips to help you accomplish the task!

Any further questions you have about RL - share them here!

Share: