analiza aiqbench
This research introduces STL-SVPG, a novel reinforcement learning framework that leverages Signal Temporal Logic to guide policy gradients in robotic tasks with sparse rewards. By using robustness metrics as trajectory-level objectives, the method effectively assigns credit for complex physical interactions and temporal constraints, outperforming prior approaches on quadcopter and manipulator benchmarks. The study demonstrates successful transfer of simulation-trained policies to real-world environments, addressing critical challenges in learning coordinated actions under strict deadlines.
Learning Robot Policies from Sparse Success Signals via STL-Guided Stein Variational Policy Gradient
arXiv:2609.31606v1 Announce Type: new Abstract: Learning robot policies for tasks with sparse success signals is challenging when completion depends on coordinated actions, precise contact outcomes, or satisfying several conditions together. Intricate physical interactions with the world further complicate these requirements. Prior work using conventional reward shaping mechanisms provides dense feedback but local progress might not translate into eventual task completion. We present Signal Temporal Logic-guided Stein Variational Policy Gradient (STL-SVPG), a population-based method that uses smooth STL robustness as a trajectory-level training objective. Differentiating this objective through the dynamics assigns credit to policy actions according to their effect on the complete task specification, rather than local progress alone. We evaluate the approach on six quadcopter and manipulator tasks that involves event-triggered responses, strictly ordered behavior, responses within specified deadlines, and physical interaction with the world. STL-SVPG achieves the highest mean success rate among the compared methods on five of six benchmarks. Simulation-trained policies trained in simulation transfer temporal and contact task behavior to the real world.
Abstract:Learning robot policies for tasks with sparse success signals is challenging when completion depends on coordinated actions, precise contact outcomes, or satisfying several conditions together. Intricate physical interactions with the world further complicate these requirements. Prior work using conventional reward shaping mechanisms provides dense feedback but local progress might not translate into eventual task completion. We present Signal Temporal Logic-guided Stein Variational Policy Gradient (STL-SVPG), a population-based method that uses smooth STL robustness as a trajectory-level training objective. Differentiating this objective through the dynamics assigns credit to policy actions according to their effect on the complete task specification, rather than local progress alone. We evaluate the approach on six quadcopter and manipulator tasks that involves event-triggered responses, strictly ordered behavior, responses within specified deadlines, and physical interaction with the world. STL-SVPG achieves the highest mean success rate among the compared methods on five of six benchmarks. Simulation-trained policies trained in simulation transfer temporal and contact task behavior to the real world.
Robotics (cs.RO)
arXiv:2609.31606 [cs.RO]
(or arXiv:2609.31606v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.31606 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 254 cuvinte
Subiecte conexe
Links #5: 2026/07
LessWrong · 31 iul. 2026
A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning
arXiv · 6 oct. 2026
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
arXiv · 7 oct. 2026
GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization
arXiv · 3 iun. 2026