Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 149% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -19% | 0% |
Use this for evidence packaging around AAMAS. Because the venue is about interaction, an artifact must make a multiagent claim inspectable: the game, the other agents, and the protocol, not just a single trained model.
opponent/population definitions, the training regime, seeds, payoff logs, proofs, or qualitative episode traces.
the supplementary zip.
commit authors for the review version.
expected outputs, per-run wall-clock, seeds, and known nondeterminism (especially in self-play).
without violating data-use terms.
The single fact that shapes packaging: a reviewer will re-run a small game far sooner than they will retrain a large policy, so make the strategic core turnkey before polishing anything.
| Claim type | First artifact inspected | Common failure caught | |---|---|---| | Convergence to an equilibrium | The game definition and the learning-rule code | Solution concept named in the paper but not encoded in the evaluation | | Emergent cooperation/defection | The environment and reward specification | Result depends on an undocumented reward-shaping constant | | Beats other agents | The opponent/population set and match protocol | Only self-play reported; no held-out opponents | | Mechanism is truthful | The payment rule plus a strategic-deviation test | No script that lets an agent try to game the mechanism |
A hypothetical submission claims a learning rule that converges to a correlated equilibrium in a repeated congestion game, shown by self-play.
rather than constants buried in a notebook, so reviewers can vary the interaction.
equilibrium-convergence claim without seeds is unfalsifiable.
drift.
measures whether it profits, because that is exactly what a game-theory reviewer will try.
script get opened, and design the top level accordingly.
current OpenReview form rather than a past year.
text[Artifact role] anonymous supplement / camera-ready release / public archive [Contents] <game/env/opponents/seeds/proofs/logs> [Anonymity risks] <paths/metadata/licenses/URLs> [Reproduction level] turnkey / scripted / descriptive / weak [Fixes before upload] <ordered list>
Other measured skills in the registry, with their headline benchmark lift.