en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Causal Reasoning and Learning Systems
Published on Nov 07, 20132462 Views
In complex real world systems, machine learning is used to influence actions, rather than just provide predictions. Those actions in turn influence the environment of the system. The goal of machine l
Related categories
Chapter list
Causal Reasoning and Learning Systems00:00
The pesky little ads00:03
Work by00:16
A complex multi-player system - 100:27
A complex multi-player system - 203:11
Learning to run a marketplace - 103:26
Learning to run a marketplace - 204:35
The feedback loop problem04:57
Toy example - 106:07
Toy example - 207:47
Toy example - 309:28
Toy example - 410:20
What is going wrong? - 111:44
What is going wrong? - 212:07
We have created a black hole!12:37
Counterfactuals, interventions, and randomization13:26
Markov factorization15:23
Markov interventions18:20
A Contextual Bandit? - 118:49
A Contextual Bandit? - 218:53
A Contextual Bandit? - 319:06
A Contextual Bandit? - 419:11
Importance sampling - 119:27
Importance sampling - 219:55
Importance sampling - 320:43
Exploration21:24
Confidence intervals - 121:33
Confidence intervals - 222:13
Confidence intervals - 323:05
Two-parts confidence interval24:26
The pesky little ads again24:54
Playing with mainline reserves - 125:42
Playing with mainline reserves - 227:04
Algorithmic toolbox27:10
Main messages29:40