AI Paper Atlas

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

Neurosymbolic Transformers for Multi-Agent Communication

Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu, Osbert Bastani, Vijay Kumar, Martin Rinard, Armando Solar-Lezama

NeurIPS 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 9 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 a synthesized programmatic communication policy with transformer retraining instead of fixed distance-based communicationNeurosymbolic transformer · random-cross and random-gridmaximum communication degreeImproved
Use a synthesized programmatic communication policy with transformer retraining instead of fixed distance-based communicationNeurosymbolic transformer · random-cross and random-gridlossNo clear effect
Use programmatic communication instead of thresholding transformer attentionNeurosymbolic transformer · random-cross and random-gridmaximum out-degreeImproved
Retrain the transformer after synthesizing the communication program (ablation)Transformer + program · random-cross and random-gridlossImproved
Use a synthesized programmatic communication policy instead of fixed distance-based communicationNeurosymbolic transformer · unlabeled goalsmaximum communication degreeImproved
Use the synthesized programmatic communication policyNeurosymbolic transformer · unlabeled goalslossHurt
Allow random-choice rules in the program search space (ablation)Programmatic communication policy · random-cross and random-gridmaximum out-degreeImproved
Allow random-choice rules in the program search space (ablation)Programmatic communication policy · unlabeled goalslossImproved
Use decision-tree communication policies instead of list-operating programsLearned communication policy · random-cross, random-grid, and unlabeled goalscommunication degreeHurt
Use policy-gradient communication decisions as actions instead of teacher-guided program synthesisCommunication policy · multi-agent planning tasksloss and communication degreeMixed

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