AI Paper Atlas

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

A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning

Arrasy Rahman, Ignacio Carlucho, Niklas Höpner, Stefano V. Albrecht

JMLR 2023 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 8 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
add GNN action-value estimation (vs QL) (ablation)Q-learning learner · FortAttack (evaluation)average return: -3.51 -> 7.01Improved
add GNN action-value estimation (vs QL) (ablation)Q-learning learner · Wolfpack (evaluation)average return: 20.57 -> 8.88Hurt
add GNN action-value estimation (vs QL) (ablation)Q-learning learner · LBF (evaluation)average return: 1.41 -> 2.07Improved
add agent model without joint action value (QL to QL-AM) (ablation)QL · Wolfpack (evaluation)average return: 20.57 -> 14.24Hurt
add agent model to GNN (GNN-AM) (ablation)GNN · Wolfpack (evaluation)average return: 8.88 -> 30.87Improved
add agent model to GNN (GNN-AM) (ablation)GNN · LBF (evaluation)average return: 2.07 -> 1.80Hurt
add joint action-value decomposition (GPL-Q vs GNN-AM) (ablation)GNN-AM · FortAttack (evaluation)average return: 8.12 -> 14.20Improved
add joint action-value decomposition (GPL-Q vs GNN-AM) (ablation)GNN-AM · Wolfpack (evaluation)average return: 30.87 -> 36.36Improved
train joint value with soft policy iteration instead of Q-learningGPL-Q · FortAttack (evaluation)average return: 14.20 -> 16.82Improved
use joint-training MARL (MADDPG) instead of GPLGPL-Q · Wolfpack (evaluation)average return: 36.36 -> 19.20Hurt
use DGN instead of GPLGPL-Q · LBF (evaluation)average return: 2.32 -> 0.64Hurt

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