Dif-MAML: Decentralized Multi-Agent Meta-Learning

Decentralized Anti-coordination Through Multi-agent Learning

To achieve an optimal outcome in many situations, agents need to choose distinct actions from one another. This is the case notably in many resource allocation problems, where a single resource can only be used by one agent at a time. How shall a designer of a multi-agent system program its identical agents to behave each in a different way? From a game theoretic perspective, such situations le...

Coordinated Multi-Agent Learning for Decentralized POMDPs

In many multi-agent applications such as distributed sensor nets, a network of agents act collaboratively under uncertainty and local interactions. Networked Distributed POMDP (ND-POMDP) provides a framework to model such cooperative multi-agent decision making. Existing work on ND-POMDPs has focused on offline techniques that require accurate models, which are usually costly to obtain in pract...

Meta-learning Processes in Multi-agent Systems

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

In reinforcement learning, agents learn by performing actions and observing their 1 outcomes. Sometimes, it is desirable for a human operator to interrupt an agent 2 in order to prevent dangerous situations from happening. Yet, as part of their 3 learning process, agents may link these interruptions, that impact their reward, to 4 specific states and deliberately avoid them. The situation is pa...

Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents

We consider the problem of fully decentralized multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the informatio...