AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs

Jiayu Chen, Jingdi Chen, Tian Lan, Vaneet Aggarwal

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use multi-agent covering options instead of single-agent options or no optionsMARL agents on multi-agent Grid Maze and Mujoco tasks · Multi-agent goal-achieving taskstime steps to complete the taskImproved
Use four-agent covering optionsDistributed Q-learning · 4-agent Grid Mazetask completion: ~400 episodesImproved
Use pairwise options rather than no options or single-agent optionsMARL agents · m × n Grid Mazelearning speed: about two orders of magnitudeImproved
Use pairwise options with Distributed Q-LearningMARL agents · 6-agent Grid Maze with random groupingtask completionHurt
Use pairwise options with Centralized Q-Learning + Force instead of Distributed Q-LearningMARL agents using pairwise options · 6-agent Grid Maze with random groupingtask completionImproved
Use Centralized Q-Learning + Force rather than Distributed Q-Learning to select optionsMARL agents using multi-agent options · Grid Maze tasksconvergence speed and final performanceImproved
Approximate the joint transition graph with a Kronecker product of individual-agent graphsMulti-agent option discovery · Grid Room approximation study, ρ=0.5Fiedler estimation accuracy: 100No clear effect
Approximate the joint transition graph with a Kronecker product of individual-agent graphsMulti-agent option discovery · Grid Room approximation study, ρ=0.2Fiedler estimation accuracy: 99.9; 96.2; 89.8; 79.4Mixed
Increase transition influence between agentsKronecker graph approximation · Grid Room approximation studyFiedler estimation accuracy, ρ=0.2: 99.9; 96.2; 89.8; 79.4Hurt
Use multi-agent options despite dynamic transition influence among agentsCentralized Q-Learning + Force · Grid Room with random grouping and collisionstask completion steps: 60-100 stepsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy