Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
read the original abstract
Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication
AsynCoMARL is a new asynchronous MARL algorithm that matches leading baselines on success and collision rates while using 26% fewer messages via graph transformers on dynamic communication graphs.
-
On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations
A survey that consolidates federated learning, multi-agent algorithms, and collaborative sensing techniques for AI on satellite constellations, including a unifying taxonomy and ongoing GitHub curation.
-
PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning
PIMbot introduces an adaptive attack using reward-channel and policy manipulation to disrupt cooperation in multi-robot social dilemma RL, shown effective in Gazebo simulation and on NVIDIA Jetson hardware.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.