Coordination-driven learning in multi-agent problem spaces

09/13/2018

∙

We discuss the role of coordination as a direct learning objective in multi-agent reinforcement learning (MARL) domains. To this end, we present a novel means of quantifying coordination in multi-agent systems, and discuss the implications of using such a measure to optimize coordinated agent policies. This concept has important implications for adversary-aware RL, which we take to be a sub-domain of multi-agent learning.

READ FULL TEXT

Coordination-driven learning in multi-agent problem spaces

Measuring collaborative emergent behavior in multi-agent reinforcement learning

Improving Multi-agent Coordination by Learning to Estimate Contention

Promoting Coordination through Policy Regularization in Multi-Agent Reinforcement Learning

Learning to Collaborate by Grouping: a Consensus-oriented Strategy for Multi-agent Reinforcement Learning

Curriculum-Driven Multi-Agent Learning and the Role of Implicit Communication in Teamwork

Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

Coordination-driven learning in multi-agent problem spaces

Related Research

Measuring collaborative emergent behavior in multi-agent reinforcement learning

Improving Multi-agent Coordination by Learning to Estimate Contention

Promoting Coordination through Policy Regularization in Multi-Agent Reinforcement Learning

Learning to Collaborate by Grouping: a Consensus-oriented Strategy for Multi-agent Reinforcement Learning

Curriculum-Driven Multi-Agent Learning and the Role of Implicit Communication in Teamwork

Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems