No article text was recorded for this version.
importance sampling variance
Version 1 of 155 papers55 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
- Blog: Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
- Blog: Learning Structured Reasoning via Tractable Trajectory Control
- Blog: Importance Resampling for Off-policy Prediction
- Blog: Off-Policy Actor-Critic with Shared Experience Replay
- Blog: Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees
- Blog: Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration
- Blog: Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration
- Blog: Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
- Blog: Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
- Blog: DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
- Blog: Self-Imitation Learning via Generalized Lower Bound Q-learning
- Blog: Off-policy Learning with Eligibility Traces: A Survey
- Blog: Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
- Blog: Double Policy Estimation for Importance Sampling in Sequence Modeling-Based Reinforcement Learning
- Blog: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
- Blog: On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation
- Blog: Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
- Blog: SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning
- Blog: Per-decision Multi-step Temporal Difference Learning with Control Variates
- Blog: CoMPS: Continual Meta Policy Search
- Blog: Batch Policy Gradient Methods for Improving Neural Conversation Models
- Blog: Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation
- Blog: Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
- Blog: Local and Adaptive Mirror Descents in Extensive-Form Games
- Blog: Safe and Efficient Off-Policy Reinforcement Learning
- Blog: Conditional Importance Sampling for Off-Policy Learning
- Blog: Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
- Blog: Exponentially Weighted Imitation Learning for Batched Historical Data
- Blog: Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization
- Blog: Towards Off-Policy Learning for Ranking Policies with Logged Feedback
- Blog: PAC-Bayesian Offline Contextual Bandits With Guarantees
- Blog: Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning
- Blog: Offline Learning in Markov Games with General Function Approximation
- Blog: Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
- Blog: GFlowNets and variational inference
- Blog: Reinforcement Learning from Imperfect Demonstrations
- Blog: Off-policy Distributional Q(λ): Distributional RL without Importance Sampling
- Blog: Constrained Policy Improvement for Efficient Reinforcement Learning
- Blog: Off-policy learning based on weighted importance sampling with linear computational complexity
- Blog: Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation
- Blog: Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation
- Blog: Symmetry Considerations for Learning Task Symmetric Robot Policies
- Blog: Off-policy Learning with Options and Recognizers
- Blog: Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
- Blog: Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
- Blog: Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning
- Blog: Hindsight policy gradients
- Blog: Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
- Blog: Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
- Blog: Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate
- Blog: RL-finetuning LLMs from on- and off-policy data with a single algorithm
- Blog: Weighted importance sampling for off-policy learning with linear function approximation
- Blog: Compound Returns Reduce Variance in Reinforcement Learning
- Blog: In-sample Actor Critic for Offline Reinforcement Learning
History & citation
Current · Permanent link
- This direction split from Stabilizing Off-Policy Learning via Importance Sampling Control (98% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_importance_sampling_variance_d25a2031,
title = {importance sampling variance},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/importance-sampling-variance/rdr_d25a203128e6440bbad058ad4eab529f},
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_importance_sampling_variance_d25a2031_v1,
title = {importance sampling variance},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/importance-sampling-variance/rdr_d25a203128e6440bbad058ad4eab529f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}