No article text was recorded for this version.
policy gradient variance
Version 1 of 11,219 papers1,417 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization
- Blog: Diagnostic Evaluation of Policy-Gradient-Based Ranking
- Blog: An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
- Blog: Stochastic Variance Reduction for Deep Q-learning
- Blog: Analyzing the Variance of Policy Gradient Estimators for the Linear-Quadratic Regulator
- Blog: Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation
- Blog: Stochastic Variance Reduction for Policy Gradient Estimation
- Blog: Bayesian Policy Gradient and Actor-Critic Algorithms
- Blog: Experimental design for MRI by greedy policy search
- Blog: On Centralized Critics in Multi-Agent Reinforcement Learning
- Blog: Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems
- Blog: Farm-gym:A modular reinforcement learning platform for stochastic agronomic games
- Blog: Clipped Action Policy Gradient
- Blog: Analysis and Improvement of Policy Gradient Estimation
- Blog: Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
- Blog: Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math
- Blog: Deep Bayesian Quadrature Policy Optimization
- Blog: Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization
- Blog: Efficient Gradient Estimation for Motor Control Learning
- Blog: Enhanced DouDiZhu Card Game Strategy Using Oracle Guiding and Adaptive Deep Monte Carlo Method
- Blog: Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator
- Blog: Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
- Blog: On Centralized Critics in Multi-Agent Reinforcement Learning
- Blog: Beyond variance reduction: Understanding the true impact of baselines on policy optimization
- Blog: Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning
- Blog: Behavior Alignment via Reward Function Optimization
- Blog: An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
- Blog: Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective
- Blog: Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
- Blog: Variance Reduction in Off-Policy Deep Reinforcement Learning using Spectral Normalization
- Blog: Global Convergence of Natural Policy Gradient with Hessian-Aided Momentum Variance Reduction
- Blog: Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
- Blog: Variance Reduction for Evolution Strategies via Structured Control Variates.
- Blog: Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems
- Blog: Improving Gradient Estimation by Incorporating Sensor Data
- Blog: Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
- Blog: An Analysis of Measure-Valued Derivatives for Policy Gradients
- Blog: Learning robust control for LQR systems with multiplicative noise via policy gradient
- Blog: An Analysis of Measure-Valued Derivatives for Policy Gradients
- Blog: Mollification Effects of Policy Gradient Methods
- Blog: On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
- Blog: Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
- Blog: The Mirage of Action-Dependent Baselines in Reinforcement Learning
- Blog: Sample-efficient Policy Optimization with Stein Control Variate
- Blog: Signal-to-Noise Ratio Analysis of Policy Gradient Algorithms
- Blog: Stabilizing Policy Gradient Methods via Reward Profiling
- Blog: Truly Deterministic Policy Optimization
- Blog: Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System
- Blog: Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines
- Blog: Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
- Blog: Deep Bayesian Quadrature Policy Optimization
- Blog: DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
- Blog: Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training
- Blog: Training Language GANs from Scratch
- Blog: An Efficient Algorithm for Deep Stochastic Contextual Bandits
- Blog: Improving Gradient Estimation by Incorporating Sensor Data
- Blog: ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret
- Blog: The Mirage of Action-Dependent Baselines in Reinforcement Learning
- Blog: Stabilized Nested Rollout Policy Adaptation
- Blog: Variance Reduction for Evolution Strategies via Structured Control Variates
Showing 60 of 1,219 papers.
History & citation
Current · Permanent link
- Stabilizing Policy Gradients for High Dimensional Reinforcement Learning merged into this direction (81% overlap)
- Variance Reduction for Sample Efficient Policy Gradients merged into this direction (94% overlap)
- Stabilizing Discrete Selection in Neural Networks merged into this direction (69% overlap)
- Policy Gradients via Analytical Integration over Action Spaces merged into this direction (69% overlap)
- Action Dependent Baselines for Policy Gradient Variance Reduction merged into this direction (79% overlap)
- Direct Variance Minimization for Policy Gradient Estimation merged into this direction (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_policy_gradient_variance_ecc96bda,
title = {policy gradient variance},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/policy-gradient-variance/rdr_ecc96bdaa66742e18ed7c792e3acb6ad},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_policy_gradient_variance_ecc96bda_v1,
title = {policy gradient variance},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/policy-gradient-variance/rdr_ecc96bdaa66742e18ed7c792e3acb6ad/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}