Loading
Life sciences · Preprint
arXiv · September 8, 2026
Early or partial results. Treat as a signal, not a conclusion.
This preprint describes HSAC, a hybrid reinforcement learning algorithm for adaptive robotic construction that handles mixed discrete and continuous action spaces. The method was evaluated in simulation against hybrid-PPO and validated in one physical two-robot experiment building a spanning arch, but lacks peer review and independent replication.
Algorithm development study with simulation benchmarking and proof-of-concept physical validation. Robotic construction domain; no human subjects or patient population.. Intervention: HSAC: reinforcement learning algorithm combining SAC with graph neural networks and unilateral edge encoding for adaptive construction sequence generation.. Compared with: Hybrid-PPO (HPPO), prior method for hybrid action spaces in construction tasks..
HSAC demonstrated significantly higher asymptotic performance than hybrid-PPO (HPPO) in simulation. Algorithm showed good sample efficiency and robustness to hyperparameter choices. Successfully handled up to 10 discrete actions without performance degradation in simulation.
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an early-stage robotics and machine learning study demonstrating proof-of-concept in simulation and a single physical experiment; it lacks independent validation, peer review, and clinical or health-relevant endpoints.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Robotic construction offers the potential to use materials more efficiently and create complex geometries, but current methods rely on rigid, high-precision plans that cannot accommodate the tolerances, inaccuracies, and unexpected changes inherent in physical fabrication. In this work, we introduce a reinforcement learning approach that forgoes predefined plans entirely, instead generating construction sequences adaptively as the structure is built. Our method operates on graph-structured state representations and a mixed (parameterized) action space, requiring both discrete block selection and continuous placement parameters. Because the stability simulation of a structure is computationally heavy, we develop an efficient exploration strategy by incorporating unilateral edges into graph neural networks, extending soft actor-critic (SAC) to this hybrid setting. We evaluate our algorithm, HSAC, against the prior method hybrid-PPO (HPPO), demonstrating significantly higher asymptotic performance and good sample efficiency. We also demonstrate HSAC's robustness to hyperparameter choices and its exploration capability, handling up to 10 discrete actions without performance degradation. Finally, we validate our approach on a physical two-robot setup, successfully building a spanning arch with 3D-printed blocks in closed-loop execution, confirming that policies trained in simulation transfer to real hardware.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.