Pith Number

pith:BAOLDG6E

pith:2026:BAOLDG6EROEA5LTS47VF7XGQY4

not attested not anchored not stored refs resolved

Learning Equilibria in Coordination Games via Minorization-Maximization

Ana Busic, Ashok Krishnan K.S., Helene Le Cadre

Regularizing coordination games with irrational individual costs creates a unique equilibrium that a minorization-maximization scheme can learn reliably.

arxiv:2605.13644 v1 · 2026-05-13 · cs.GT

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BAOLDG6EROEA5LTS47VF7XGQY4}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

This selected equilibrium is shown to be an ε-equilibrium of the original game, where ε is parametrized by the regularizing function. A minorization-maximization based iterative learning scheme is proposed to learn equilibria in this game. This scheme converges to the potential-optimal equilibrium, and has superior convergence behaviour in comparison to gradient and best response methods.

C2weakest assumption

The multi-equilibrium game can be regularized so that it possesses a strictly concave potential function that selects a unique equilibrium; the agents' irrational perception of individual costs is modeled in a way that preserves the potential-game structure after regularization.

C3one line summary

Regularizing multi-equilibrium coordination games with a strictly concave potential selects a unique epsilon-equilibrium that a minorization-maximization scheme learns with faster convergence than standard alternatives.

References

39 extracted · 39 resolved · 0 Pith anchors

[1] R. Cooper, Coordination games. Cambridge university Press, 1999 1999

[2] Aggregative games and best-reply potenti als, 2010

[3] Voorneveld, Potential games and interactive decisions with multiple cr iteria 1999

[4] Achieving a Collective Target through In- centives, 2025

[5] Exploration in deep reinforcement learning: From single-agent to multi agent domain, 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:17.561674Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

081cb19bc48b880eae72e7ea5fdcd0c71857bd6addea59b963e195367b4790b5

Aliases

arxiv: 2605.13644 · arxiv_version: 2605.13644v1 · doi: 10.48550/arxiv.2605.13644 · pith_short_12: BAOLDG6EROEA · pith_short_16: BAOLDG6EROEA5LTS · pith_short_8: BAOLDG6E

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/BAOLDG6EROEA5LTS47VF7XGQY4 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 081cb19bc48b880eae72e7ea5fdcd0c71857bd6addea59b963e195367b4790b5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3cea0948b870dd3eb146e3d7cc65eec35977aa1f76c0194a08e3323f874c6386",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.GT",
    "submitted_at": "2026-05-13T15:06:06Z",
    "title_canon_sha256": "537a1a2761d15e48262cc687b9b58a3adb3fd671ce5544f6943df355a5399cd6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13644",
    "kind": "arxiv",
    "version": 1
  }
}