Pith Number

pith:WDN37A2C

pith:2026:WDN37A2CPHVWSGUB3MV65FD7FP

not attested not anchored not stored refs resolved

Trajectory-Level Data Augmentation for Offline Reinforcement Learning

Matthias Burkhardt, Tobias Schm\"ahling, Tobias Windisch

A trajectory-level augmentation technique lets offline reinforcement learning succeed from limited suboptimal trajectories by using geometric relationships between rewards, value functions, and logging policies.

arxiv:2605.13401 v1 · 2026-05-13 · cs.LG · cs.RO · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WDN37A2CPHVWSGUB3MV65FD7FP}

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 introduce a trajectory-based augmentation technique that exploits task structure and the geometric relationship between rewards, value functions, and mathematical properties of logging policies, enabling training of off-policy models from a limited number of suboptimal trajectories.

C2weakest assumption

That a usable geometric relationship between rewards, value functions, and logging policies exists and can be reliably exploited for augmentation without introducing bias that harms downstream policy performance.

C3one line summary

Trajectory-based data augmentation exploits geometric relationships between rewards, values, and logging policies to enable effective offline RL from few suboptimal trajectories.

References

40 extracted · 40 resolved · 3 Pith anchors

[1] Alignment of decam-like large survey telescope for real-time active optics and error analysis 2021 · doi:10.1016/j.optcom.2020.126685

[2] Hindsight experience replay 2017

[3] J., Smith, L., Kostrikov, I., and Levine, S 2023

[4] Automated assembly of camera modules using active alignment with up to six degrees of freedom 2014 · doi:10.1117/12.2041754

[5] Active alignments of lens systems with reinforcement learning, 2025 2025

Receipt and verification

First computed	2026-05-18T02:44:47.595567Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b0dbbf834279eb691a81db2bee947f2bdc017e3cea6b3306ebd03773dbc378b8

Aliases

arxiv: 2605.13401 · arxiv_version: 2605.13401v1 · doi: 10.48550/arxiv.2605.13401 · pith_short_12: WDN37A2CPHVW · pith_short_16: WDN37A2CPHVWSGUB · pith_short_8: WDN37A2C

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/WDN37A2CPHVWSGUB3MV65FD7FP \
  | 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: b0dbbf834279eb691a81db2bee947f2bdc017e3cea6b3306ebd03773dbc378b8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "57fcdc6117cbe8b5a6b55291cd12679ae34ec357ad1ead39c4777cb295365996",
    "cross_cats_sorted": [
      "cs.RO",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:57:17Z",
    "title_canon_sha256": "fbd76bd25f76e8c694782388eade601380ff01a6a8ea91d891bd780b26dec969"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13401",
    "kind": "arxiv",
    "version": 1
  }
}