Adaptive Sampling using Stein's Discrepancy

Project Description
Investigation into the usage of different sampling methods based on Stein’s discrepancy in the context of Curriculum Learning.
Implemented both a gradient-based approach (Stein’s Variational Gradient Descent1) and a direct minimization method (Stein Points2) in jax and evaluated them on different RL baselines.
-
Liu et al., Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm ↩︎
-
Chen et al., Stein Points ↩︎