LESSWRONG
LW

290
RAISE
1211510
Message
Dialogue
Subscribe

Road to AI Safety Excellence. Our mission is to make studying AI as easy as possible, in whatever way. Right now, we're developing an online course for AI Safety.

More info: https://www.aisafety.info/ . Inspiration: https://distill.pub/2017/research-debt/ and https://slatestarcodex.com/2017/11/09/ars-longa-vita-brevis/

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy
RAISE7y20

Thanks for the note.

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

Will edit the post to make that clear

Reply
18RAISE AI Safety prerequisites map entirely in one post
6y
5
18Our plan for 2019-2020: consulting for AI Safety education
6y
15
2IRL 8/8: Generative Adversarial Imitation Learning
6y
0
7IRL 7/8: Generalizing human-robot cooperation: Cooperative IRL
7y
0
4IRL 6/8: Querying the human: Active Reward Learning
7y
0
7IRL 5/8: Maximum Causal Entropy IRL
7y
2
6[Link] IDA: 11-14/14: Future Directions
7y
0
4IRL 4/8: Maximum Entropy IRL and Bayesian IRL
7y
0
4[Link] IDA 9/14: The Scheme
7y
0
6IRL 3/8: Mitigating degeneracy: feature matching
7y
0
Load More