Hacker News new | comments | show | ask | jobs | submit | from login
You Cannot Serve Two Masters: The Harms of Dual Affiliation (argmin.net)
255 points by stochastician 70 days ago | past | web | 79 comments
You Cannot Serve Two Masters: The Harms of Dual Affiliation (argmin.net)
2 points by myinnerbanjo 70 days ago | past | web
An Outsider's Tour of Reinforcement Learning (argmin.net)
4 points by pjrule 89 days ago | past | web
Clues for Which I Search and Choose (argmin.net)
1 point by pjrule 4 months ago | past | web
The Ethics of Reward Shaping (argmin.net)
1 point by wei_jok 6 months ago | past | web
Random Search vs. Model-Free RL (argmin.net)
2 points by jonbaer 6 months ago | past | web
An Outsider's Tour of Reinforcement Learning (argmin.net)
3 points by onuralp 7 months ago | past | web
Random Search Beats Reinforcement Learning in MuJoCo (argmin.net)
3 points by huevosabio 7 months ago | past | web
Clues for Which I Search and Choose (argmin.net)
3 points by soap4151 7 months ago | past | web
A Model, You Know What I Mean? (argmin.net)
1 point by twtw 7 months ago | past | web
An Outsider's Tour of Reinforcement Learning (argmin.net)
2 points by ghosthamlet 7 months ago | past | web
“A Model, You Know What I Mean?”, Model-Based vs. Model-Free RL (argmin.net)
2 points by huevosabio 7 months ago | past | web
Make It Happen (argmin.net)
2 points by sharemywin 7 months ago | past | web
The Policy of Truth: Efficiency of Policy Gradients (argmin.net)
2 points by huevosabio 7 months ago | past | web
Reinforcement Learning, Policy Gradient Is Nothing More Than Random Search (argmin.net)
2 points by dspoka 8 months ago | past | web
Policy gradient is a bad algorithm (argmin.net)
2 points by stochastician 8 months ago | past | web
An Outsider’s Tour of Reinforcement Learning (argmin.net)
3 points by jonbaer 8 months ago | past | web
Lessons from Optics, the Other Deep Learning (argmin.net)
531 points by mxwsn 8 months ago | past | web | 94 comments
Lessons from Optics, The Other Deep Learning (argmin.net)
3 points by bmc7505 8 months ago | past | web
Lessons from Optics, the Other Deep Learning (argmin.net)
2 points by daralthus 8 months ago | past | web
Lessons from Optics, the Other Deep Learning (argmin.net)
1 point by gk1 8 months ago | past | web
Lessons from Optics, the Other Deep Learning (argmin.net)
3 points by billconan 8 months ago | past | web
Lessons from Optics, the Other Deep Learning (argmin.net)
3 points by mxwsn 8 months ago | past | web
Reflections on Random Kitchen Sinks (argmin.net)
1 point by sampo 9 months ago | past | web
Reflections on Random Kitchen Sinks (NIPS “Test of Time” Award Speech) (argmin.net)
2 points by carljv 10 months ago | past | web
An Addendum to Alchemy (argmin.net)
2 points by tim_sw 10 months ago | past | web
Evolutionary strategies or DFO? (argmin.net)
1 point by stochastician on Apr 3, 2017 | past | web
[flagged] The Fall of Big Data (argmin.net)
35 points by henridf on Nov 14, 2016 | past | web | 32 comments
Twitter for Model Selection (argmin.net)
2 points by stochastician on Apr 26, 2016 | past | web
Ben Recht (optimization professor at Berkeley) starts writing a blog (argmin.net)
2 points by elexhobby on Apr 11, 2016 | past | web

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

Search: