pith:PBCCOPAW
Gradient Iterated Temporal-Difference Learning
Gradient Iterated Temporal-Difference learning takes full gradients through moving targets to match semi-gradient speeds on Atari and other benchmarks.
arxiv:2603.07833 v2 · 2026-03-08 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{PBCCOPAWRYZSAK5LKT5OF6ADIK}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our evaluation reveals that this algorithm, called Gradient Iterated Temporal-Difference learning, has a competitive learning speed against semi-gradient methods across various benchmarks, including Atari games, a result that no prior work on gradient TD methods has demonstrated.
That computing gradients through the sequence of moving targets in iterated TD will not introduce new instabilities or require prohibitive extra computation that negates the speed gains.
Gradient Iterated TD learning stabilizes iterated TD by computing gradients over moving targets and achieves competitive speed to semi-gradient methods on Atari games and other benchmarks.
Formal links
Receipt and verification
| First computed | 2026-05-17T23:38:59.721803Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
7844273c168e33202bab54fae2f80342b2a19f4e770f4ac12d3443bd35f28ab3
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/PBCCOPAWRYZSAK5LKT5OF6ADIK \
| 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: 7844273c168e33202bab54fae2f80342b2a19f4e770f4ac12d3443bd35f28ab3
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0ca02a3b61d2a42b6a813a19748660ebb62740cc78a6b57920cdd07b02ac0ab8",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-03-08T22:32:15Z",
"title_canon_sha256": "58cb096c3b848f4b6416f53316d28dfb6a73f1bbe740f237ca51e916c82e9bc5"
},
"schema_version": "1.0",
"source": {
"id": "2603.07833",
"kind": "arxiv",
"version": 2
}
}