Search Results for author:
Found 3 papers, 1 papers with code
CoinRun: Solving Goal Misgeneralisation
Goal misgeneralisation is a key challenge in AI alignment -- the task of getting powerful Artificial Intelligences to align their goals with human intentions and human morality.
The Expertise Problem: Learning from Specialized Feedback
RLHF algorithms that learn from multiple teachers therefore face an expertise problem: the reliability of a given piece of feedback depends both on the teacher that it comes from and how specialized that teacher is on relevant components of the task.
CULT: Continual Unsupervised Learning with Typicality-Based Environment Detection
We introduce CULT (Continual Unsupervised Representation Learning with Typicality-Based Environment Detection), a new algorithm for continual unsupervised learning with variational auto-encoders.
