# Variance-Reduced Off-Policy Memory-Efficient Policy Search

arXiv: https://arxiv.org/abs/2009.06548 · HTML: https://mlsanity.com/paper/2009.06548/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality](https://mlsanity.com/paper/2102.11866/) (2021)
- [Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint](https://mlsanity.com/paper/2101.02137/) (2021)
- [On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction](https://mlsanity.com/paper/2106.00993/) (2021)
- [Enhancing PPO with Trajectory-Aware Hybrid Policies](https://mlsanity.com/paper/2502.15968/) (2025)
- [A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using L-λ Smoothness](https://mlsanity.com/paper/2307.15892/) (2023)
- [Variance Reduction based Experience Replay for Policy Optimization](https://mlsanity.com/paper/2208.12341/) (2022)

## Abstract (arXiv)

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and store a large ``reference'' batch of samples from time to time. To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples. Empirical studies validate the effectiveness of the proposed approaches.