+ Create new tricision Login 

Login

or


Forgot password?

First visit? Sign-up now!

By continuing you accept the Terms & Conditions and Privacy Policy.

time is up

RL + Recommender Systems Panel

Ask experts questions about RL + RecSys. Panelists: Alekh Agarwal (Microsoft), Ed Chi (Google), Maria Dimakopoulou (Netflix), Georgios Theocharous (Adobe); Co-Chairs/Moderators: Minmin Chen and Lihong Li. Panel discussion time: 18:00-19:00, July 23 EDT (Boston time). https://sites.google.com/view/RL4RealLife


saved
Ideas
Pros and cons
 
Votes
What are the biggest challenges in applying RL for recommender systems?
 
dealing with open vs. closed world assumptions during attribution.
by ed chi
1
 
2
Vote
LL
MD
What are the biggest advantages of RL compared to other learning paradigms for recommender systems?
1
Vote
LL
What is the gap between academic research in RL and real world applications of RL? How can we close the gap?
1
Vote
LL
Is the RL framing suitable for recommendations with multiple stakeholders? Are we learning interaction policies or better to frame as mechanism design?
by AS
0
Vote
What is the future of RL in Recommender Systems? Is there the end - the situation when the problem is either solved, or no further improvement is possible/needed?
by Danil
0
Vote
What were the biggest breakthroughs in RL in recent years? How about realizing RL in real-world recommender systems?
0
Vote
What do you think are the next opportunities or research directions that can further enable RL for real world RecSys applications?
0
Vote

Comments

https://www.tricider.com/brainstorming/2mmod1j4APh