On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “SVRPG”

Stochastic Variance-Reduced Policy Gradientcs.LG

A new algorithm for reinforcement learning using SVRPG.

problem Solving Markov Decision Processes (MDPs) with policy gradient methods.

method Stochastic variance-reduced policy gradient (SVRPG) algorithm.

result SVRPG achieves linear convergence under increasing batch sizes.

reinforcement learning policy gradient stochastic variance-reduced Markov Decision Processes SVRPG

2018-06-14abs ↗pdf ↗

An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradientcs.LG

Improved SVRPG analysis for faster convergence in reinforcement learning.

problem Finding faster convergence in reinforcement learning algorithms.

method Improved convergence analysis of SVRPG method, focusing on variance reduction and epoch length/batch size parameters.

result Improved convergence to ε-approximate stationary point with reduced sample complexity.

reinforcement learning policy gradient stochastic variance-reduced convergence analysis sample complexity

2019-05-29abs ↗pdf ↗