1

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

We propose a novel framework and algorithm for cheap talk discovery (CTD) and cheap talk utilization (CTU).

Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota, Jakob Nicolaus Foerster, Shimon Whiteson

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

Discovered Policy Optimisation

In this paper we explore the Mirror Learning space by meta-learning a “drift” function.

Chris Lu, Jakub Kuba, Alistair Letcher, Luke Metz, Christian Schroeder de Witt, Jakob Foerster

Equivariant Networks for Zero-Shot Coordination

We present a novel equivariant network architecture for use in Dec-POMDPs that prevents the agent from learning policies which break symmetries, doing so more effectively than prior methods.

Darius Muglich, Christian Schroeder de Witt, Elise van der Pol, Shimon Whiteson, Jakob Foerster

Equivariant Networks for Zero-Shot Coordination

Rainbench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery

We introduce RainBench, a new multi-modal benchmark dataset for data-driven precipitation forecasting.

Christian Schroeder de Witt, Catherine Tong, Valentina Zantedeschi, Daniele De Martini, Alfredo Kalaitzis, Matthew Chantry, Duncan Watson-Parris, Piotr Bilinski

Rainbench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery

FACMAC: Factored Multi-Agent Centralised Policy Gradients

We propose multi-agent common knowledge reinforcement learning (MACKRL).

Bei Peng, Tabish Rashid, Christian Schroeder de Witt, Pierre-Alexandre Kamienny, Philip Torr, Wendelin Boehmer, Shimon Whiteson

FACMAC: Factored Multi-Agent Centralised Policy Gradients

Multi-Agent Common Knowledge Reinforcement Learning

We propose multi-agent common knowledge reinforcement learning (MACKRL).

Christian Schroeder de Witt, Jakob N. Foerster, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson

The Starcraft Multi-Agent Challenge

We propose the StarCraft Multi-Agent Challenge (SMAC) to measure real progress in MARL.

Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim GJ Rudner, Chia-Man Hung, Philip HS Torr, Jakob Foerster, Shimon Whiteson

The ZX-Calculus is Incomplete for Quantum Mechanics

We prove that the ZX-calculus is incomplete for quantum mechanics.

Christian Schroeder de Witt, Vladimir Zamdzhiev