Quasi-Monte Carlo Initialization for Meta-Reinforcement Learning
Julian G. Soltes
cs.LG math.OC
Abstract
This paper explores the efficacy of quasi-Monte Carlo (QMC) weight initialization for meta-reinforcement learning within modern benchmark environments. Various sampling methods are used to bound a population-based search and aggregate an optimal prior from a baseline set of tasks. The QMC meta-priors show improvements in training convergence compared to modern orthogonal (SB3) defaults when extrapolated to similar unseen continuous control environments. In dissimilar tasks, the orthogonal orientation was globally superior for an unbiased search.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.