AI Paper Atlas

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

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Can Chang, Ni Mu, Jiajun Wu, Ling Pan, Huazhe Xu

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 2 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
Guide agents with parallel programs and learned task allocationE-MAPP · Overcooked seen tasks in novel maps, Hardcompletion rate: 0.00% -> 56.3%Improved
Guide agents with parallel programs and learned task allocationE-MAPP · Overcooked unseen tasks in novel maps, Hardcompletion rate: 0.0% -> 43.7%Improved
Add a feasibility predictor (ablation)E-MAPP · Overcooked hard taskscompletion rate: 38.5% -> 56.3%Improved
Add a feasibility predictor (ablation)E-MAPP · Overcooked hard tasksaverage score: 1.42 ± 0.56 -> 1.58 ± 0.60Improved
Add a reachability predictor (ablation)E-MAPP · Overcooked hard tasksaverage timesteps: 23.37 -> 17.6Improved
Add a reachability predictor (ablation)E-MAPP · Overcooked hard taskscompletion rate: 43.8% -> 56.3%Improved
Add a cost-to-go predictor (ablation)E-MAPP · Overcooked hard tasksaverage timesteps: 20.42 -> 17.6Improved
Add a cost-to-go predictor (ablation)E-MAPP · Overcooked hard taskscompletion rate: 52.0% -> 56.3%Improved
Use parallel rather than sequential programs (ablation)E-MAPP · Overcooked hard tasksaverage timesteps: 20.33 -> 17.6Improved
Use parallel rather than sequential programs (ablation)E-MAPP · Overcooked hard taskscompletion rate: 48.8% -> 56.3%Improved
Use E-MAPP in a partially observable setting instead of its original full-observation settingE-MAPP · Overcooked hard taskscompletion rate: 56.3% -> 27.1%Hurt
Use E-MAPP rather than MAPPOOvercooked hard tasks · Overcooked hard tasksaverage score: 0.59± 0.27 -> 1.58 ± 0.60Improved

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