AI Paper Atlas

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

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

El Mahdi El Mhamdi, Rachid Guerraoui, Hadrien Hendrikx, Alexandre Maurer

NeurIPS 2017 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 17 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 neutral learning rule with interruption-compatible explorationJoint action learners · Decentralized multi-agent reinforcement learningdynamic safe interruptibilityImproved
Use independent Q-learners without pruning interrupted observationsIndependent learners · Two-agent coordination matrix gamedynamic safe interruptibilityHurt
Provide an interruption signal and prune observations from interrupted stepsIndependent learners · Decentralized multi-agent reinforcement learningdynamic safe interruptibilityImproved

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