AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions

Michael Chang, Sid Kaushik, S. Matthew Weinberg, Tom Griffiths, Sergey Levine

ICML 2020 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 7 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 cloned society with redundant primitives (ablation)Vickrey society · Chainglobal returnImproved
Use the cloned CCV implementation rather than other tested implementations (ablation)Cloned Vickrey society · Chainsample efficiencyImproved
Add redundant primitives (ablation)CCV society · Dualityglobal returnImproved
Use cloned CCV society instead of monolithic baselinesTwo Rooms · Two Rooms pre-training and transfer taskssample efficiencyImproved
Use cloned CCV society instead of a hierarchical monolithic baselineTwo Rooms transfer task · Two Roomsweight change during transferImproved
Use cloned primitives with independently parameterized bidding policies rather than shared policy weights (ablation)Cloned society · Market MDP experimentsglobal performanceNo clear effect
Use a solitary society rather than a cloned society (ablation)Vickrey society · Market Banditbid accuracyHurt
Use a solitary society rather than a cloned society (ablation)Vickrey society · Chainglobal returnHurt
Use the Environment Reward objective instead of auction utility (ablation)Society · Market Banditbid accuracyHurt
Use the first-price auction instead of the cloned Vickrey mechanism (ablation)Society · Market Banditbid accuracyHurt
Use solitary Vickrey instead of cloned Vickrey (ablation)Society · Market Banditglobal policy qualityHurt
Use a monolithic learner instead of cloned CCV societyTwo Rooms · Two Rooms pre-training and transfer taskssample efficiencyHurt

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