Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by seb_ruder on 2018-09-13 (UTC).

David Silver on Principles for Reinforcement Learning at the #DLIndaba2018. Important principles that are not only applicable to RL, but to ML research in general. E.g. leaderboard-driven research vs. hypothesis-driven research (see the slides below). pic.twitter.com/EN5yiKeuCY

— Sebastian Ruder (@seb_ruder) September 13, 2018
thought
by seb_ruder on 2018-09-13 (UTC).

Principle 2. How an algorithm scales is more important than its starting point. Avoid performance ceilings. Deep Learning is successful because it scales so effectively.
Principles are meant to be controversial. I would argue that sample efficiency is at least as important. pic.twitter.com/jtjHmOcKlS

— Sebastian Ruder (@seb_ruder) September 13, 2018
thought
by seb_ruder on 2018-09-13 (UTC).

Principle 3. Generality (how your algorithm performs on other tasks) is super important. Key is to design a diverse set of challenging tasks.
This. We should evaluate on out of distribution data and new tasks. pic.twitter.com/EGBDIJSMuj

— Sebastian Ruder (@seb_ruder) September 13, 2018
thought
by seb_ruder on 2018-09-13 (UTC).

Principle 4. Use agent's experience rather than human expertise. Don't rely on engineered features or heuristics.
Hmm. Maybe true in the setting where you can sample an infinite number of experiences but domain expertise and inductive biases are important when data is limited. pic.twitter.com/sWrwB69djE

— Sebastian Ruder (@seb_ruder) September 13, 2018
thought

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib