Fast Regularized Policy Mirror Descent with One-Step TD Updates
cs.LG, math.OC
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization
- Functional Acceleration for Policy Mirror Descent
- Value Mirror Descent for Reinforcement Learning
- Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
- On the Policy Convergence of Policy Mirror Descent Methods
- Policy Mirror Descent with Temporal Difference Learning: Sample Complexity under Online Markov Data
- On the Convergence of Policy in Unregularized Policy Mirror Descent
- Elementary Analysis of Policy Gradient Methods
- On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation
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