Metraipolis › archive › dc_40eafefe6c83
Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learning — arXiv:2609.09492
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09492
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T11:11:31.879Z
- SHA-256 of the archived text
d001a69c5a0e29452ce0a91a75c1fbf51494e5ea434b1b428c65110f3cf5aa8c- Stable URL of this page
https://metraipolis.com/documento/dc_40eafefe6c83
How to cite
Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learning — arXiv:2609.09492 — arXiv (en), https://arxiv.org/abs/2609.09492 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40eafefe6c83 (Metraipolis archive dc_40eafefe6c83, sha256 d001a69c5a0e29452ce0a91a75c1fbf51494e5ea434b1b428c65110f3cf5aa8c)
BibTeX
@misc{dc40eafefe6c83,
title = {Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learning — arXiv:2609.09492},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09492},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40eafefe6c83; sha256 d001a69c5a0e29452ce0a91a75c1fbf51494e5ea434b1b428c65110f3cf5aa8c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09492. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning has produced capable controllers across a broad range of legged-robot tasks, but a subset of these tasks fail to converge under standard training: those for which most exploration trajectories terminate before producing useful gradient signal. To address such tasks we introduce the \emph{Actuator Dynamics Curriculum}, a procedure that initializes joint stiffness at a high value and anneals it toward the system-identified value as completed episode lengths grow. Using a cart-pole system as a representative example, we show that higher closed-loop joint natural frequency under critical damping enlarges the viability kernel of the underlying Markov Decision Process, increasing the fraction of initial states from which the task is feasible. We validate the kernel monotonicity on the cart-pole and apply the curriculum to a quadrupedal-to-handstand transition on the Boston Dynamics Spot, a narrow-viability task where training under fixed identified stiffness plateaus at a policy that never completes the transition. The trained policy executes the transition in simulation across 10 seeds and transfers to hardware. More broadly, our results suggest that simulated actuator dynamics is a useful axis along which to design curricula for tasks in which exploration is bottlenecked by termination conditions rather than by reward signal.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.09492 — 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 2026-10-16T10:19:11.880Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).