Deep Multi-Agent Reinforcement Learning

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

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

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.

This thesis presents a number of significant contributions deep multi-agent reinforcement for cooperative control within the framework of centralised training with decentralised execution and two associated novel benchmark suites.

we suggest a novel reinforcement learning setting that can be used to efficiently generate arbitrary adversarial perturbations using deep multi-agent reinforcement learning.

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

We used deep multi-agent reinforcement learning to solve an energy systems wargame wherein players simulate IOC decision-making.

This paper introduces Multi-Agent Mujoco, an easily extensible multi-agent benchmark suite for robotic control in continuous action spaces

We demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches.

We used deep multi-agent reinforcement learning to solve an energy systems wargame wherein players simulate IOC decision-making.