Metraipolis › archive › dc_ccab33af28cd

Temporally Interpretable Differentiable Decision Trees — arXiv:2610.10367

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10367
License (as archived): CC0-1.0
Archived: 2026-10-08T12:36:23.790Z
SHA-256 of the archived text: 9231d9b18e44a4377f206af995c089c10306240e8392ab2785cfabec0ca2faa1
Stable URL of this page: https://metraipolis.com/documento/dc_ccab33af28cd

How to cite

Temporally Interpretable Differentiable Decision Trees — arXiv:2610.10367 — arXiv (en), https://arxiv.org/abs/2610.10367 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccab33af28cd (Metraipolis archive dc_ccab33af28cd, sha256 9231d9b18e44a4377f206af995c089c10306240e8392ab2785cfabec0ca2faa1)

BibTeX

@misc{dcccab33af28cd,
  title = {Temporally Interpretable Differentiable Decision Trees — arXiv:2610.10367},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10367},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccab33af28cd; sha256 9231d9b18e44a4377f206af995c089c10306240e8392ab2785cfabec0ca2faa1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10367. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model. Within sequential-decision making tasks, differentiable decision trees (DDTs) are one approach to such interpretability, maintaining automatic-differentiable policies while providing humans with a discrete tree-based visualization. Nonetheless, current implementations of DDTs are not well-suited for sequential-decision making domains, as there exists an inherent mismatch between a tree's single-timestep behavior and a human's multi-timestep planning. Our work thus introduces time as a new dimension of interpretability, coined as temporal interpretability, and demonstrates how temporal abstractions via action chunking improve it. We achieve this by first introducing two novel policy gradient algorithms that incorporate action chunking. Additionally, to maintain parameter-efficient trees, we develop an information-theoretic tree restructuring algorithm that modifies the tree during training. Across four simulation environments, we find that warm-starting action chunked DDTs from a distilled action chunked policy is the most effective way to obtain temporally interpretable trees: they match neural network policies in three of the four domains while using up to 80$\%$ fewer parameters. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.10367 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:14:15.339Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).