Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas

26 September 2018

Papers citing "Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas"

1 / 1 papers shown

Title
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning Jakob N. Foerster Nantas Nardelli Gregory Farquhar Triantafyllos Afouras Philip Torr Pushmeet Kohli Shimon Whiteson OffRL 131 595 0 28 Feb 2017