No article text was recorded for this version.
Lagrangian optimization instability
Version 2 of 2181 papers199 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- Blog: Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality
- Blog: A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
- Blog: Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual
- Blog: Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics
- Blog: Direct Behavior Specification via Constrained Reinforcement Learning
- Blog: Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
- Blog: Constraints Penalized Q-Learning for Safe Offline Reinforcement Learning
- Blog: Discovering Diverse Nearly Optimal Policies withSuccessor Features
- Blog: Evaluating Model-Free Reinforcement Learning toward Safety-Critical Tasks
- Blog: ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
- Blog: Off-Policy Primal-Dual Safe Reinforcement Learning
- Blog: Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking
- Blog: Constrained Variational Policy Optimization for Safe Reinforcement Learning
- Blog: Augmented Proximal Policy Optimization for Safe Reinforcement Learning
- Blog: Truly No-Regret Learning in Constrained MDPs
- Blog: Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
- Blog: Two Phase $Q-$learning for Bidding-based Vehicle Sharing
- Blog: Line-Search Filter Differential Dynamic Programming for Optimal Control with Nonlinear Equality Constraints
- Blog: Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL
- Blog: Asymptotic Analysis of Weighted Fair Division
- Blog: Penalized Proximal Policy Optimization for Safe Reinforcement Learning
- Blog: Sample-Driven Federated Learning for Energy-Efficient and Real-Time IoT Sensing
- Blog: Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
- Blog: Constrained Policy Optimization
- Blog: Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
- Blog: CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
- Blog: POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning
- Blog: Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning
- Blog: CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
- Blog: One-Shot Safety Alignment for Large Language Models via Optimal Dualization
- Blog: GUARD: A Safe Reinforcement Learning Benchmark
- Blog: Benchmarking Constraint Inference in Inverse Reinforcement Learning
- Blog: Constrained Reinforcement Learning for Short Video Recommendation
- Blog: Safe reinforcement learning of dynamic high-dimensional robotic tasks: navigation, manipulation, interaction
- Blog: Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
- Blog: Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
- Blog: Constrained Reinforcement Learning via Policy Splitting
- Blog: IPO: Interior-point Policy Optimization under Constraints
- Blog: ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
- Blog: Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
- Blog: Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning
- Blog: Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
- Blog: Constrained Online Convex Optimization with Polyak Feasibility Steps
- Blog: Online Convex Optimization with Perturbed Constraints: Optimal Rates against Stronger Benchmarks
- Blog: e-COP : Episodic Constrained Optimization of Policies
- Blog: Non-Convex Feedback Optimization With Input and Output Constraints
- Blog: AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization
- Blog: Offline Safe Reinforcement Learning Using Trajectory Classification
- Blog: A Dynamic Penalty Function Approach for Constraints-Handling in Reinforcement Learning
- Blog: Constrained Policy Optimization via Bayesian World Models
- Blog: COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
- Blog: AL-CoLe: Augmented Lagrangian for Constrained Learning
- Blog: Safe Reinforcement Learning Using Advantage-Based Intervention
- Blog: CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
- Blog: Confronting Reward Model Overoptimization with Constrained RLHF
- Blog: Stepwise Alignment for Constrained Language Model Policy Optimization
- Blog: Safe Driving via Expert Guided Policy Optimization
- Blog: Optimization Issues in KL-Constrained Approximate Policy Iteration
- Blog: Projections for Approximate Policy Iteration Algorithms
Showing 60 of 181 papers.
History & citation
Current · Permanent link
- Last-Iterate Convergence for Constrained Reinforcement Learning merged into this direction (50% overlap)
- PID-stabilized Lagrangian optimization split from this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_lagrangian_optimization_instability_20faa724,
title = {Lagrangian optimization instability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/lagrangian-optimization-instability/rdr_20faa724138446818c78e34f2cce0fb8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_lagrangian_optimization_instability_20faa724_v2,
title = {Lagrangian optimization instability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/lagrangian-optimization-instability/rdr_20faa724138446818c78e34f2cce0fb8/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}