AI Paper Atlas

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

Scaling Laws for a Multi-Agent Reinforcement Learning Model

Oren Neumann, Claudius Gros

ICLR 2023 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 3 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
Increase neural network parameter countAlphaZero · Connect Four and Pentagoplaying strength: α_N: Connect Four $0.88$; Pentago $0.87$Improved
Increase training compute while using optimally sized agentsAlphaZero · Connect Four and Pentagoplaying strength: α_C: $0.55$ for both gamesImproved
Scale model size with the available compute budgetAlphaZero · Connect Four and Pentagooptimal model size: α_C^opt: Connect Four $0.62$; Pentago $0.63$Improved
Use a larger neural network at the same amount of training dataAlphaZero · Connect Four and PentagoElo scoreImproved
Increase model size on OwareAlphaZero · OwareElo score: α_N $0.75$Mixed
Increase model size on OwareAlphaZero · OwareElo scoreHurt
Use test-set value or policy loss as the performance indicator instead of EloAlphaZero · Connect Four solver-generated test setperformance prediction: 0.336No clear effect
Train beyond the compute-optimal point until convergenceAlphaZero · Connect FourElo score per fixed compute budgetHurt

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