University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Benefits and Shortcomings of Assistance

Benefits and Shortcomings of Assistance

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Elre Oldewage.

Assistance games (also known as cooperative inverse RL) enable a single RL policy to both infer human preferences and act such that they are optimized. The idea is to model the human as a part of the environment, and the true reward function as a latent variable in the environment that the agent may make inferences about. Our talk will introduce the assistance paradigm, compare it to reward learning, and discuss its flaws in the context of AI Alignment.

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity