No article text was recorded for this version.
primal-dual saddle-point formulation
Version 1 of 121 papers26 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Proximal Gradient Temporal Difference Learning Algorithms
- Blog: On Convergence of Gradient Expected Sarsa(λ)
- Blog: Provably Efficient Neural GTD for Off-Policy Learning
- Blog: Finite-Sample Analysis of Proximal Gradient TD Algorithms
- Blog: Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
- Blog: Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random
- Blog: Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity
- Blog: SVRG for Policy Evaluation with Fewer Gradient Evaluations
- Blog: Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization
- Blog: Minimax Weight and Q-Function Learning for Off-Policy Evaluation
- Blog: Stochastic Variance Reduction Methods for Policy Evaluation
- Blog: Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions
- Blog: Regularized Off-Policy TD-Learning
- Blog: Convergent TREE BACKUP and RETRACE with Function Approximation
- Blog: Finite sample analysis of the GTD Policy Evaluation Algorithms in Markov Setting
- Blog: New Versions of Gradient Temporal-Difference Learning
- Blog: Variational Policy Gradient Method for Reinforcement Learning with General Utilities
- Blog: Smoothed Dual Embedding Control
- Blog: Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration
- Blog: Distributed Policy Evaluation Under Multiple Behavior Strategies
- Blog: Variance Reduced Policy Evaluation with Smooth Function Approximation
History & citation
Current · Permanent link
- This direction split from linear function approximation constraint (71% overlap)
- This direction split from Primal-Dual Reinforcement Learning via Convex Reformulation (81% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_primal_dual_saddle_point_formulation_5010648b,
title = {primal-dual saddle-point formulation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/primal-dual-saddle-point-formulation/rdr_5010648b315b41b5ae4db4d35e8ba6fc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_primal_dual_saddle_point_formulation_5010648b_v1,
title = {primal-dual saddle-point formulation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/primal-dual-saddle-point-formulation/rdr_5010648b315b41b5ae4db4d35e8ba6fc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}