pith:3IIHZ4GZ
Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
MA-BC partitions conflicting expert data and pools the rest to recover Pareto-optimal policies faster than separate learners in multi-objective imitation.
arxiv:2605.12000 v2 · 2026-05-12 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3IIHZ4GZWOEVRIP6X3HNUOLNFP}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently, and is minimax optimal.
The provided demonstrations come from Pareto-optimal experts in a MOMDP, and that observable conflicts in state-action pairs can be reliably partitioned without additional structure on the transition dynamics or reward functions.
MA-BC partitions divergent expert data while pooling non-conflicting pairs in MOMDPs, converging faster to Pareto-optimal policies than independent learners and matching a new minimax lower bound.
Receipt and verification
| First computed | 2026-05-20T00:05:47.245557Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3IIHZ4GZWOEVRIP6X3HNUOLNFP \
| 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: da107cf0d9b38958a1febeceda396d2bcb65b90926c5c4efb802d2349092aa26
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "c6b6dd7ef44777e1af2feadaec44b11215e99812b630757889a4f96c9b338b57",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-12T11:49:08Z",
"title_canon_sha256": "0c17dc9eafbce2a8a12f8c525fd0b65071b56d6fcc8bffd00211e1ce7ea48fab"
},
"schema_version": "1.0",
"source": {
"id": "2605.12000",
"kind": "arxiv",
"version": 2
}
}