Hacker News new | past | comments | ask | show | jobs | submit login
Challenges of real-world reinforcement learning (acolyer.org)
48 points by motivic 8 months ago | hide | past | favorite | 5 comments

Reinforcement learning without simulation is not feasible for complex problems.

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

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?

The Deep RL Bootcamp lectures are still good and relevant:


beggars can't be choosers of course but i would prefer something to read rather than something to watch

Applications are open for YC Winter 2021

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact