method · first seen 9 Oct 2026
variance reduction in policy gradient
Also: variance-reduced policy gradient
Techniques that reduce gradient estimation variance in policy gradient reinforcement learning using recursive or off-policy estimators.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Variance-Reduced Policy Gradient is Nearly Minimax-OptimalPapers · 9 Oct 2026 · Leonardo Cesani, Matteo Papini, Marcello Restelli
Latest sources
- Variance-Reduced Policy Gradient is Nearly Minimax-OptimalPapers · 9 Oct 2026 · Leonardo Cesani, Matteo Papini, Marcello Restelli