arXiv Machine Learning

Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic

arXiv:2607. 08899v1 Announce Type: cross Abstract: Signal Temporal Logic (STL) is increasingly used to describe interpretable objectives and constraints for optimal control and learning methods, especially when no target time series data is available.

arXiv AI

Jul 14

Learning Linear Temporal Specifications from Demonstrations with Uncertainty

arXiv:2607. 10918v1 Announce Type: new Abstract: Learning temporal logic specifications from system demonstrations is essential for tasks such as formal verification and controller synthesis, especially in safety-critical domains.

By Parastou Fahim, Constantino Lagoa, R\^omulo Meira-G'oes

benchmarks safety

arXiv AI

Aug 17

Reward Machines for Signal Temporal Logic

arXiv:2608. 13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction.

By Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai

agents reinforcement-learning

arXiv AI

Sep 2

On Synthesis of Metric Interval Temporal Logics

arXiv:2609.01032v1 Announce Type: cross Abstract: Automated mining of formal specifications is vital for verifying real-time systems. However, existing passive learning approaches remain restricted t...

By Hsi-Ming Ho, Shankaranarayanan Krishna, Khushraj Madnani

benchmarks

arXiv AI

Aug 26

Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives

arXiv:2304.10041v2 Announce Type: replace Abstract: This work investigates formal policy synthesis for continuous-state stochastic dynamic systems subject to high-level specifications expressed in li...

By Lening Li, Zhentian Qian, Jianan Xia, Qiren Geng, Huasheng Zhang, Liang Hu, Qishuang Li, Junqiang Lou

reinforcement-learning efficiency

arXiv AI

Jun 6

From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution

arXiv:2604. 12474v3 Announce Type: replace-cross Abstract: In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission.

By Lidor Erez, Shahaf S. Shperberg, Ayal Taitler

agents reinforcement-learning robotics

arXiv Machine Learning

Jun 25

Certified Robust Invariant Polytope Training in Neural Controlled ODEs

arXiv:2408. 01273v3 Announce Type: replace Abstract: We propose a framework for training neural network controllers with certified robust forward invariant polytopes.

By Akash Harapanahalli, Samuel Coogan

rag benchmarks

arXiv Machine Learning

Aug 17

hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance

arXiv:2608. 13678v1 Announce Type: cross Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime.

By Moritz Zoellner, Anastasios Manganaris, Ahmed H. Qureshi, Rohan Paleja

diffusion robotics safety

arXiv AI

Jun 9

Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies

arXiv:2606. 08312v1 Announce Type: new Abstract: In this work we study offline reinforcement learning (RL) under temporally extended task constraints expressed in Linear Temporal Logic over finite traces (LTLf).

By Ashkan Ansarifard (Sapienza University of Rome), Matteo Mancanelli (Sapienza University of Rome), Elena Umili (Sapienza University of Rome), Fabio Patrizi (Sapienza University of Rome)

llms reinforcement-learning safety

arXiv Machine Learning

Jun 9

Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control

arXiv:2512. 01467v2 Announce Type: replace Abstract: Controlling autonomous systems under real-world conditions often requires policies that can be evaluated with low latency and minimal energy consumption.

By Fabian Kresse, Christoph H. Lampert

agents efficiency benchmarks

arXiv Machine Learning

Sep 22

Augmenting PID Control with Deep Reinforcement Learning: A Hybrid Approach to the Industrial Benchmark

The paper proposes a hybrid PID–Deep Reinforcement Learning (DRL) controller for industrial processes, addressing the limitations of traditional PID controllers in complex, non‑linear, multi‑input environments. Using the Industrial Benchmark (IB) to test DRL, the authors develop a multi‑objective reward function and employ a TD3 agent to discover optimal settings for the IB’s ‘Gain’ and ‘Shift’ parameters. These parameters are then fed into a tuned PID controller, yielding a system that combines the optimal performance and efficiency of DRL with the reliability of classical control.

By Zhengyang (Cissy), Gu, Joseph E. Hernandez, John Burtenshaw, Sean Scott, Thomas Cook, Chris Couch

agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Jul 6

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs

Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process.

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Sep 1

Generalization as a robust performance property of learning-enabled dynamical systems

arXiv:2608.30431v1 Announce Type: cross Abstract: By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization...

By Filippo Fabiani

Related stories