Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- GPT-4 Technical Report
- Momentum-Based Policy Gradient with Second-Order Information
- Stochastic Variance Reduction for Policy Gradient Estimation
- Stochastic Recursive Momentum for Policy Gradient Methods
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks