Reinforcement Learning (RL), and more recently Deep Reinforcement Learning, achieved impressive results in many domains, such as AlphaGo (2016) and AlphaZero (2017). Like a human, Reinforcement Learning agents learn for themselves to achieve successful strategies that lead to the optimal long-term rewards. This error and trial learning strategy is the key differentiator between RL methodologies and the other traditional ML approaches. In this presentation, we propose an introduction to Reinforcement Learning and Deep RL, the main recent achievements and techniques, and the most salient challenges faced by the RL community to scale and deploy these systems in the real world.

Please join @Sarah Boufelja in this on demand webinar for Introduction to Reinforcement and Deep Reinforcement Learning: DSE Presents Chat with the Lab webinar.
​
Share any of your questions below and register to watch here. 

Thanks,

------------------------------
JORGE CASTANON
Chat with labs webinar series: https://ibm.co/Chat-With-The-Lab-Webinar
------------------------------
#GlobalAIandDataScience
#GlobalDataScience

Hi everyone, 
You can watch the on demand recording here and download the slides here. 



Please share any of your questions below.

------------------------------
Meighann Helene
------------------------------

Original Message:
Sent: Wed June 16, 2021 12:18 PM
From: JORGE CASTANON
Subject: Introduction to Reinforcement and Deep Reinforcement Learning: DSE Presents Chat with the Lab

Reinforcement Learning (RL), and more recently Deep Reinforcement Learning, achieved impressive results in many domains, such as AlphaGo (2016) and AlphaZero (2017). Like a human, Reinforcement Learning agents learn for themselves to achieve successful strategies that lead to the optimal long-term rewards. This error and trial learning strategy is the key differentiator between RL methodologies and the other traditional ML approaches. In this presentation, we propose an introduction to Reinforcement Learning and Deep RL, the main recent achievements and techniques, and the most salient challenges faced by the RL community to scale and deploy these systems in the real world.

Please join @Sarah Boufelja in this on demand webinar for Introduction to Reinforcement and Deep Reinforcement Learning: DSE Presents Chat with the Lab webinar.
​
Share any of your questions below and register to watch here. 

Thanks,

------------------------------
JORGE CASTANON
Chat with labs webinar series: https://ibm.co/Chat-With-The-Lab-Webinar
------------------------------
#GlobalAIandDataScience
#GlobalDataScience

Any github page to see the related codes and in process work? ... Any links?

------------------------------
Dave Vaidehi Nirmalkumar
------------------------------

Original Message:
Sent: Wed June 16, 2021 12:18 PM
From: JORGE CASTANON
Subject: Introduction to Reinforcement and Deep Reinforcement Learning: DSE Presents Chat with the Lab

Reinforcement Learning (RL), and more recently Deep Reinforcement Learning, achieved impressive results in many domains, such as AlphaGo (2016) and AlphaZero (2017). Like a human, Reinforcement Learning agents learn for themselves to achieve successful strategies that lead to the optimal long-term rewards. This error and trial learning strategy is the key differentiator between RL methodologies and the other traditional ML approaches. In this presentation, we propose an introduction to Reinforcement Learning and Deep RL, the main recent achievements and techniques, and the most salient challenges faced by the RL community to scale and deploy these systems in the real world.

Please join @Sarah Boufelja in this on demand webinar for Introduction to Reinforcement and Deep Reinforcement Learning: DSE Presents Chat with the Lab webinar.
​
Share any of your questions below and register to watch here. 

Thanks,

------------------------------
JORGE CASTANON
Chat with labs webinar series: https://ibm.co/Chat-With-The-Lab-Webinar
------------------------------
#GlobalAIandDataScience
#GlobalDataScience