Link to: Media Analytics
MEDIA ANALYTICS
Link to: MA Projects
PROJECTS
Link to: MA People
PEOPLE
Link to: MA Publications
PUBLICATIONS
Link to: MA Patents
PATENTS
Learning to Simulate
ICLR 2019 | Simulation can be a useful tool when obtaining and annotating train data is costly. However, optimal tuning of simulator parameters can itself be a laborious task. We implement a meta-learning algorithm in which a reinforcement learning agent, as the met learner, automatically adjusts the parameters of a non-differentiable simulator, thereby controlling the distribution of synthesized data in order to maximize the accuracy of a model trained on that data.
Collaborators: Nataniel Ruiz, Samuel Schulter, Manmohan Chandraker
