pith:IYYGEQYI
Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination
Dream-MPC refines a few policy-rollout trajectories via gradient ascent inside a learned world model to raise overall task performance.
arxiv:2605.04568 v2 · 2026-05-06 · cs.LG · cs.AI · cs.RO
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IYYGEQYIKJZ547255DSSWREN7Z}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our results on 24 continuous control tasks show that Dream-MPC can significantly improve the performance of the underlying policy and can outperform gradient-free MPC and state-of-the-art baselines.
The learned world model is sufficiently accurate and differentiable that gradient ascent on rolled-out trajectories reliably improves performance without being misled by model errors or local optima.
Dream-MPC boosts underlying policies on 24 continuous control tasks by optimizing policy-generated trajectories with gradient ascent, uncertainty regularization, and temporal amortization inside a latent world model.
Receipt and verification
| First computed | 2026-05-25T02:01:21.619872Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
46306243085273de7f5de8e52b448dfe7dcaee771d01773e0800d44bd945530b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IYYGEQYIKJZ547255DSSWREN7Z \
| 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: 46306243085273de7f5de8e52b448dfe7dcaee771d01773e0800d44bd945530b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "b601aed29fbd7d25fadca9352d056cdb7c42af1fe561f93e9ca9cf19c2980a09",
"cross_cats_sorted": [
"cs.AI",
"cs.RO"
],
"license": "http://creativecommons.org/licenses/by-sa/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-06T07:13:11Z",
"title_canon_sha256": "10edec659906056595f8435feb3dabf1501bab40dc053cbdf663f40b8cd86fbc"
},
"schema_version": "1.0",
"source": {
"id": "2605.04568",
"kind": "arxiv",
"version": 2
}
}