Pith Number

pith:YRRAMBCS

pith:2026:YRRAMBCSV6N7FRBQPYXSDEKN4R

not attested not anchored not stored refs pending

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

Lute Lillo, Nick Cheney

Maintaining archives of diverse policies in a shared latent space preserves plasticity in continual reinforcement learning.

arxiv:2604.15414 v2 · 2026-04-16 · cs.LG · cs.AI · cs.NE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YRRAMBCSV6N7FRBQPYXSDEKN4R}

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

In our MiniGrid CL setting, TeLAPA learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative.

C2weakest assumption

That organizing policies into behaviorally diverse neighborhoods via a shared latent space will reliably preserve plasticity and transfer better than single-model preservation across a wide range of continual RL domains and interference patterns.

C3one line summary

TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.

Receipt and verification

First computed	2026-06-10T01:08:35.445009Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa

Aliases

arxiv: 2604.15414 · arxiv_version: 2604.15414v2 · doi: 10.48550/arxiv.2604.15414 · pith_short_12: YRRAMBCSV6N7 · pith_short_16: YRRAMBCSV6N7FRBQ · pith_short_8: YRRAMBCS

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/YRRAMBCSV6N7FRBQPYXSDEKN4R \
  | 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: c462060452af9bf2c4307e2f21914de442ef06c3c7eb296a896034909f09d8aa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "70747f82ce3b80c13704025f935cc09399e3c4d0b489caa3754d21dac4522897",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.NE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-16T17:06:54Z",
    "title_canon_sha256": "6c57bfe0876c73341a1ce4467f8d84cf5f1c6262a2fbb3748ecf118c9dc27bf8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.15414",
    "kind": "arxiv",
    "version": 2
  }
}