Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics

Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics

Asilomar Conference on Signals, Systems and Computers (ACSSC), 2022

3 December 2022

Enrique Mallada

ArXiv (abs)PDF HTML

Papers citing "Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics"

3 / 3 papers shown

Title
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning Alessandro Montenegro Marco Mussi Matteo Papini Alberto Maria Metelli BDL 157 2 0 15 Jul 2024
Dissipative Gradient Descent Ascent Method: A Control Theory Inspired Algorithm for Min-max OptimizationIEEE Control Systems Letters (L-CSS), 2024 Tianqi Zheng Nicolas Loizou Pengcheng You Enrique Mallada 249 4 0 14 Mar 2024
Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPsNeural Information Processing Systems (NeurIPS), 2023 Dongsheng Ding Chen-Yu Wei Jianchao Tan Alejandro Ribeiro 302 28 0 20 Jun 2023