Pith Number

pith:TVTKIJ5S

pith:2025:TVTKIJ5SFEPIQA27ODCVPOUP2Y

not attested not anchored not stored refs pending

High entropy leads to symmetry-equivariant policies in Dec-POMDPs

Andreas Bulling, Constantin Ruhdorfer, Jakob Foerster, Johannes Forkel, Michael Beukman

Sufficiently high entropy regularization in any Dec-POMDP makes policy gradient flow with tabular softmax converge to the same symmetry-equivariant joint policy from every initialization.

arxiv:2511.22581 v5 · 2025-11-27 · cs.LG · cs.MA

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TVTKIJ5SFEPIQA27ODCVPOUP2Y}

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

We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initialization, to the same joint policy, and that this joint policy is equivariant w.r.t. all symmetries of the Dec-POMDP.

C2weakest assumption

The assumption that entropy regularization is 'sufficiently high' to force convergence to the unique equivariant policy under tabular softmax parametrization in arbitrary Dec-POMDPs.

C3one line summary

High entropy regularization guarantees convergence to symmetry-equivariant policies in Dec-POMDPs, making cross-play returns match self-play returns.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Finding the Time to Think: Learning Planning Budgets in Real-Time RL

Receipt and verification

First computed	2026-06-08T01:03:51.786624Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9d66a427b2291e88035f70c557ba8fd62f3c5c1308ccb732e2ff94724e1b4d49

Aliases

arxiv: 2511.22581 · arxiv_version: 2511.22581v5 · doi: 10.48550/arxiv.2511.22581 · pith_short_12: TVTKIJ5SFEPI · pith_short_16: TVTKIJ5SFEPIQA27 · pith_short_8: TVTKIJ5S

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/TVTKIJ5SFEPIQA27ODCVPOUP2Y \
  | 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: 9d66a427b2291e88035f70c557ba8fd62f3c5c1308ccb732e2ff94724e1b4d49

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "819c6b1c9354a7f25db8dc7ab33bd055709d415f1534be8346080dd82694cc12",
    "cross_cats_sorted": [
      "cs.MA"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-11-27T16:13:27Z",
    "title_canon_sha256": "c2a96431595a94e9af6a69640f799e7d9b707b5ec410a680d7dc97b49647592e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.22581",
    "kind": "arxiv",
    "version": 5
  }
}