News for hackers. Stuff that matters.
Re:Challenges of real-world reinforcement learning by orasis on Monday January 13, 2020 @06:06PM (#22039766)
Reinforcement learning without simulation is not feasible for complex problems.

If you can’t simulate, stick to multi-armed bandits.

Re:Challenges of real-world reinforcement learning by throwlaplace on Monday January 13, 2020 @03:10PM (#22038096)
anyone know a good survey paper about current SOA? i've read sutton&barton, skimmed openai "Spinning Up in Deep RL". anything else out there?
Re:Challenges of real-world reinforcement learning by hcrisp on Monday January 13, 2020 @05:51PM (#22039631)
The Deep RL Bootcamp lectures are still good and relevant:

https://sites.google.com/view/deep-rl-bootcamp/lectures

Re:Challenges of real-world reinforcement learning by throwlaplace on Monday January 13, 2020 @06:12PM (#22039811)
beggars can't be choosers of course but i would prefer something to read rather than something to watch
Re:Challenges of real-world reinforcement learning by orasis on Monday January 13, 2020 @06:31PM (#22039986)