Search Results for author:
Found 5 papers, 2 papers with code
Unsupervised language models for disease variant prediction
There is considerable interest in predicting the pathogenicity of protein variants in human genes.
Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences
As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers.
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning
Robots can learn the right reward function by querying a human expert.
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning
We then adapt the dynamical model with samples from this policy in the real environment.
Learning Reward Functions by Integrating Human Demonstrations and Preferences
In a user study, we compare our method to a standard IRL method; we find that users rated the robot trained with DemPref as being more successful at learning their desired behavior, and preferred to use the DemPref system (over IRL) to train the robot.
