Posts

RAISE AI Safety prerequisites map entirely in one post 2019-07-17T08:57:18.226Z · score: 17 (8 votes)
Our plan for 2019-2020: consulting for AI Safety education 2019-06-03T16:51:27.534Z · score: 21 (15 votes)
IRL 8/8: Generative Adversarial Imitation Learning 2019-04-22T15:02:09.779Z · score: 2 (1 votes)
IRL 7/8: Generalizing human-robot cooperation: Cooperative IRL 2019-04-15T10:13:32.565Z · score: 7 (4 votes)
IRL 6/8: Querying the human: Active Reward Learning 2019-04-08T13:49:05.908Z · score: 4 (2 votes)
IRL 5/8: Maximum Causal Entropy IRL 2019-04-04T10:53:31.792Z · score: 8 (2 votes)
[Link] IDA: 11-14/14: Future Directions 2019-03-28T18:56:47.784Z · score: 6 (3 votes)
IRL 4/8: Maximum Entropy IRL and Bayesian IRL 2019-03-25T22:07:29.012Z · score: 4 (2 votes)
[Link] IDA 9/14: The Scheme 2019-03-21T18:28:09.745Z · score: 4 (2 votes)
IRL 3/8: Mitigating degeneracy: feature matching 2019-03-18T20:15:47.657Z · score: 6 (3 votes)
IDA 5-8/14: Approval Directed Agents 2019-03-14T23:58:12.079Z · score: 4 (2 votes)
AI Safety Prerequisites Course: Basic abstract representations of computation 2019-03-13T19:38:56.301Z · score: 32 (10 votes)
IRL 2/8: Mitigating degeneracy: multiple experimentation 2019-03-11T13:33:21.857Z · score: 14 (5 votes)
IDA 1-4/14: Problem Statement 2019-03-07T14:02:01.642Z · score: 9 (3 votes)
IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy 2019-03-04T13:11:45.287Z · score: 23 (6 votes)

Comments

Comment by raise on IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy · 2019-03-04T17:03:55.742Z · score: 2 (2 votes) · LW · GW

Thanks for the note.

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

Will edit the post to make that clear