AI Paper Atlas

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

MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents

Stephen Chung

NeurIPS 2021 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 1 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 MAP propagation instead of REINFORCETeam of agents · Acrobot-v1average return: -148.42 -> -100.29Improved
Use MAP propagation instead of REINFORCETeam of agents · CartPole-v1average return: 47.29 -> 459.70Improved
Use MAP propagation instead of REINFORCETeam of agents · LunarLander-v2average return: -62.05 -> 127.88Improved
Use MAP propagation instead of REINFORCETeam of agents · MountainCarContinuous-v0average return: -35.52 -> 39.45Improved
Use MAP propagation instead of backpropActor-critic network · Acrobot-v1average return: -106.29 -> -100.29Improved
Use MAP propagation instead of backpropActor-critic network · CartPole-v1average return: 458.96 -> 459.70Improved
Use MAP propagation instead of backpropActor-critic network · LunarLander-v2average return: 104.92 -> 127.88Improved
Use MAP propagation instead of backpropActor-critic network · MountainCarContinuous-v0average return: 4.30 -> 39.45Improved
Add target-output information to the MAP learning rule (ablation)MAP propagation on scalar regression · Scalar regressionlearning speedImproved
Use negative L2 loss as reward rather than the target-informed Appendix C rule (ablation)MAP propagation on scalar regression · Scalar regressionlearning speedHurt
Use target-informed MAP propagation rather than backpropScalar regression · Scalar regressionasymptotic performanceHurt

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