1323

LESSWRONG
LW

1322

IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy — LessWrong

Inverse Reinforcement LearningReinforcement learningRoad To AI Safety Excellence

20

IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy

4th Mar 2019

1 min read

20

This is a linkpost for https://app.grasple.com/#/level/1495

20

IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy

New Comment

2 comments, sorted by

Click to highlight new comments since: Today at 3:47 PM

[-]cousin_it7y50

Behind a login wall.

Thanks for the note.

One can create an account through the overview link, this one.

Will edit the post to make that clear

More from RAISE

Curated and popular this week

Inverse Reinforcement LearningReinforcement learningRoad To AI Safety Excellence

Every Monday for 8 weeks, we will be posting lessons about Inverse Reinforcement Learning. This is lesson 1.

Note that access to the lessons requires creating an account here.

To help students get up to speed, we have also published 2 supplementary lessons that cover prerequisite material:

The POMDP
Bellman equations

Have a nice day!