Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients

27 April 2021

Papers citing "Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients"

2 / 2 papers shown

Title
MAVEN: Multi-Agent Variational Exploration Anuj Mahajan Tabish Rashid Mikayel Samvelyan Shimon Whiteson DRL 135 355 0 16 Oct 2019
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning Jakob N. Foerster Nantas Nardelli Gregory Farquhar Triantafyllos Afouras Philip H. S. Torr Pushmeet Kohli Shimon Whiteson OffRL 111 595 0 28 Feb 2017