Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear
Quadratic Games

v1v2 (latest)

Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games

8 July 2019

Eric Mazumdar

Lillian J. Ratliff

Michael I. Jordan

S. Shankar Sastry

ArXiv (abs)PDF HTML

Papers citing "Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games"

12 / 12 papers shown

Title
Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games Kai Zhang Zhuoran Yang Tamer Basar 82 127 0 31 May 2019
On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games Eric V. Mazumdar Michael I. Jordan S. Shankar Sastry 99 120 0 03 Jan 2019
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems Dhruv Malik A. Pananjady Kush S. Bhatia K. Khamaru Peter L. Bartlett Martin J. Wainwright 51 199 0 20 Dec 2018
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments S. Srinivasan Marc Lanctot V. Zambaldi Julien Perolat K. Tuyls Rémi Munos Michael Bowling 59 149 0 21 Oct 2018
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning Max Jaderberg Wojciech M. Czarnecki Iain Dunning Luke Marris Guy Lever ... Joel Z Leibo David Silver Demis Hassabis Koray Kavukcuoglu T. Graepel OffRL 112 727 0 03 Jul 2018
On Gradient-Based Learning in Continuous Games Eric Mazumdar Lillian J. Ratliff S. Shankar Sastry 104 136 0 16 Apr 2018
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator Maryam Fazel Rong Ge Sham Kakade M. Mesbahi 82 609 0 15 Jan 2018
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning Marc Lanctot V. Zambaldi A. Gruslys Angeliki Lazaridou K. Tuyls Julien Perolat David Silver T. Graepel 116 638 0 02 Nov 2017
Emergent Complexity via Multi-Agent Competition Trapit Bansal J. Pachocki Szymon Sidor Ilya Sutskever Igor Mordatch 70 390 0 10 Oct 2017
On the Sample Complexity of the Linear Quadratic Regulator Sarah Dean Horia Mania Nikolai Matni Benjamin Recht Stephen Tu 73 579 0 04 Oct 2017
Cycles in adversarial regularized learning P. Mertikopoulos Christos H. Papadimitriou Georgios Piliouras 64 322 0 08 Sep 2017
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments Ryan J. Lowe Yi Wu Aviv Tamar J. Harb Pieter Abbeel Igor Mordatch 162 4,509 0 07 Jun 2017