Pith Number

pith:SRJ44VVR

pith:2026:SRJ44VVRY67BJ7Y7SLBCJ6QEV2

not attested not anchored not stored refs resolved

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling

Josiah P. Hanna, Nicholas E. Corrado, Wenyuan Huang

Adaptive sampling of hard tasks via a minimax objective improves worst-case performance in multi-task reinforcement learning.

arxiv:2605.14350 v1 · 2026-05-14 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SRJ44VVRY67BJ7Y7SLBCJ6QEV2}

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 benchmarks like MetaWorld-MT10 and MT50, DRATS improves data efficiency and increases worst-task performance compared to existing task sampling algorithms.

C2weakest assumption

That adaptively sampling tasks furthest from being solved via the derived minimax objective will consistently lead to improved overall learning without causing instability or requiring additional assumptions about task difficulty.

C3one line summary

DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.

References

299 extracted · 299 resolved · 37 Pith anchors

[1] Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

[2] Advances in Neural Information Processing Systems , volume=

[3] arXiv preprint arXiv:2408.14037 , year=

[4] Under review , volume=

[5] Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization 1911 · arXiv:1911.08731

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:08.077945Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9453ce56b1c7be14ff1f92c224fa04aeab080d6b66123f71a0865fa06c7174e2

Aliases

arxiv: 2605.14350 · arxiv_version: 2605.14350v1 · doi: 10.48550/arxiv.2605.14350 · pith_short_12: SRJ44VVRY67B · pith_short_16: SRJ44VVRY67BJ7Y7 · pith_short_8: SRJ44VVR

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/SRJ44VVRY67BJ7Y7SLBCJ6QEV2 \
  | 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: 9453ce56b1c7be14ff1f92c224fa04aeab080d6b66123f71a0865fa06c7174e2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f68d578e90315e981806d3165f42c93a3865aa17434c1e32d1ab1dd74e332aef",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T04:22:24Z",
    "title_canon_sha256": "a274d0337ed4a04fde459cca36a3ade46fc83684b67668132cd55949409bc954"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14350",
    "kind": "arxiv",
    "version": 1
  }
}