AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Dynamic population-based meta-learning for multi-agent communication with natural language

Abhinav Gupta, Marc Lanctot, Angeliki Lazaridou

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Emergent communication in referential games · 4 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 dynamic population-based meta-learning instead of prior methodsReferential game agents · MSCOCO image game test captionsBLEU: 28.4 ± 0.32 -> 29.3 ± 0.25Improved
Use dynamic population-based meta-learning instead of prior methodsReferential game agents · IWSLT'14 English-German text gameBLEU: 23.9 ± 0.21 -> 25.2 ± 0.16Improved
Use top-k sampling instead of greedy decodingPretrained text-game speaker · IWSLT'14 English-German text gameBLEU: 20.8 ± 0.06 -> 24.6 ± 0.05Improved
Use dynamic population-based meta-learning rather than PretrainedReferential game agents · Flickr8k cross-task test (trained on MSCOCO)referential accuracy: 59.7 ± 0.9 -> 70.2 ± 1.8Improved
Use dynamic population-based meta-learning rather than PretrainedReferential game agents · Flickr8k within-task testreferential accuracy: 65.3 ± 0.3 -> 78.9 ± 1.4Improved
Add interaction with the meta-agent when building the agent population (ablation)Dynamic population-based meta-learning · MSCOCO image game testreferential accuracyImproved
Train the meta-agent iteratively instead of resetting its weights and training from scratch (ablation)Dynamic population-based meta-learning · MSCOCO image game testreferential accuracyImproved
Integrate interactive and supervised learning in separate phases rather than the full method's grounding setup (ablation)Dynamic population-based meta-learning · MSCOCO image game testreferential accuracyNo clear effect
Use FOMAML or Reptile instead of MAML (ablation)Dynamic population-based meta-learning · MSCOCO image gamereferential accuracyNo clear effect

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