domains / families / research / aamas-artifact-evaluation

aamas-artifact-evaluation

separate

Use when packaging AAMAS multiagent code, environments, opponent and population sets, random seeds, game definitions, and logs as anonymous supplementary evidence or a public post-acceptance release, even without a separate artifact badge, so that game-theory and MARL reviewers can inspect and re-run the interaction claims.

When to use

• packaging AAMAS multiagent code
• preparing anonymous supplementary evidence
• creating public post-acceptance releases
• documenting game definitions and opponent sets
• anonymizing repository history and metadata
• creating minimal reproduction maps
• packaging self-play studies
• documenting strategic-deviation tests

When not to use

• packaging single trained models without interaction context
• violating data-use terms for human-subject settings

Skill page

Source