Metraipolis › archive › dc_b04ef158a4dc

IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning — arXiv:2608.10634

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10634
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:25.301Z
SHA-256 of the archived text
e666631187cfe080c4ab3ca29564f8f121daa8a32c6210676b8f4e84606cb05b
Stable URL of this page
https://metraipolis.com/documento/dc_b04ef158a4dc

How to cite

IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning — arXiv:2608.10634 — arXiv (en), https://arxiv.org/abs/2608.10634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b04ef158a4dc (Metraipolis archive dc_b04ef158a4dc, sha256 e666631187cfe080c4ab3ca29564f8f121daa8a32c6210676b8f4e84606cb05b)
BibTeX
@misc{dcb04ef158a4dc,
  title = {IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning — arXiv:2608.10634},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10634},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b04ef158a4dc; sha256 e666631187cfe080c4ab3ca29564f8f121daa8a32c6210676b8f4e84606cb05b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making. Numerous methods have been developed to improve dynamics prediction and policy optimization for MBRL through uncertainty estimation, model regularization, and conservative value learning. However, these methods typically treat the transition model and critic as monolithic predictors, overlooking the policy-induced data bias. Consequently, action can become entangled with environmental evolution, while uneven action coverage may distort the counterfactual value estimates used for policy improvement. To address this, we propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR). IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization. Its latent and state-aligned components are identifiable up to an invertible within-block transformation and pointwise, respectively. For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional. TR augments the critic with an action-density-scaled residual correction and optimizes a targeted loss, yielding doubly robust policy-gradient estimation when either the critic or the replay action density is consistently specified. Extensive experiments on five MuJoCo tasks show that IADD-TR achieves competitive returns with improved sample efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10634 — 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 2026-10-19T06:11:45.090Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).