English
Related papers

Related papers: Globally Stable Neural Imitation Policies

200 papers

Mastering complex sequential tasks continues to pose a significant challenge in robotics. While there has been progress in learning long-horizon manipulation tasks, most existing approaches lack rigorous mathematical guarantees for ensuring…

Robotics · Computer Science 2024-10-08 Alexandre St-Aubin , Amin Abyaneh , Hsiu-Chin Lin

We present a new family of deep neural network-based dynamic systems. The presented dynamics are globally stable and can be conditioned with an arbitrary context state. We show how these dynamics can be used as structured robot policies.…

Robotics · Computer Science 2020-12-14 Julen Urain , Davide Tateo , Tianyu Ren , Jan Peters

The goal of this paper is to analyze Long Short Term Memory (LSTM) neural networks from a dynamical system perspective. The classical recursive equations describing the evolution of LSTM can be recast in state space form, resulting in a…

Systems and Control · Electrical Eng. & Systems 2020-05-29 Fabio Bonassi , Enrico Terzi , Marcello Farina , Riccardo Scattolini

With a growing interest in data-driven control techniques, Model Predictive Control (MPC) provides an opportunity to exploit the surplus of data reliably, particularly while taking safety and stability into account. In many real-world and…

Artificial Intelligence · Computer Science 2021-06-04 Mayank Mittal , Marco Gallieri , Alessio Quaglino , Seyed Sina Mirrazavi Salehian , Jan Koutník

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many…

Systems and Control · Electrical Eng. & Systems 2021-12-08 Fangda Gu , He Yin , Laurent El Ghaoui , Murat Arcak , Peter Seiler , Ming Jin

State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the…

Machine Learning · Statistics 2024-12-17 Jiahe Lin , George Michailidis

Designing two-sided matching mechanisms is challenging when practical demands for matching outcomes are difficult to formalize and the designed mechanism must satisfy theoretical conditions. To address this, prior work has proposed a…

Artificial Intelligence · Computer Science 2025-07-31 Ryota Maruo , Koh Takeuchi , Hisashi Kashima

Learning algorithms have shown considerable prowess in simulation by allowing robots to adapt to uncertain environments and improve their performance. However, such algorithms are rarely used in practice on safety-critical systems, since…

Systems and Control · Computer Science 2018-10-02 Spencer M. Richards , Felix Berkenkamp , Andreas Krause

The study of provable adversarial robustness for deep neural networks (DNNs) has mainly focused on static supervised learning tasks such as image classification. However, DNNs have been used extensively in real-world adaptive tasks such as…

Machine Learning · Computer Science 2022-05-31 Aounon Kumar , Alexander Levine , Soheil Feizi

Spiking neural networks (SNNs) are gaining popularity in deep learning due to their low energy budget on neuromorphic hardware. However, they still face challenges in lacking sufficient robustness to guard safety-critical applications such…

Neural and Evolutionary Computing · Computer Science 2024-06-03 Jianhao Ding , Zhiyu Pan , Yujia Liu , Zhaofei Yu , Tiejun Huang

Deep learning has had a far reaching impact in robotics. Specifically, deep reinforcement learning algorithms have been highly effective in synthesizing neural-network controllers for a wide range of tasks. However, despite this empirical…

Robotics · Computer Science 2021-09-30 Hongkai Dai , Benoit Landry , Lujie Yang , Marco Pavone , Russ Tedrake

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences,…

Machine Learning · Statistics 2017-03-09 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

This work presents an approach to synthesize a Lyapunov-like function to ensure incrementally input-to-state stability ($\delta$-ISS) property for an unknown discrete-time system. To deal with challenges posed by unknown system dynamics, we…

Systems and Control · Electrical Eng. & Systems 2025-01-13 Ahan Basu , Bhabani Shankar Dey , Pushpak Jagtap

Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions. Unfortunately, global stability guarantees are hard to provide in dynamical systems learned from data,…

Deep neural networks are increasingly used as an effective parameterization of control policies in various learning-based control paradigms. For continuous-time optimal control problems (OCPs), which are central to many decision-making…

Machine Learning · Computer Science 2025-11-04 Joshua Hang Sai Ip , Georgios Makrygiorgos , Ali Mesbah

Deep reinforcement learning agents achieve state-of-the-art performance in a wide range of simulated control tasks. However, successful applications to real-world problems remain limited. One reason for this dichotomy is because the learnt…

Machine Learning · Computer Science 2024-11-27 Rory Young , Nicolas Pugeault

Adversarial detection is designed to identify and reject maliciously crafted adversarial examples(AEs) which are generated to disrupt the classification of target models. Presently, various input transformation-based methods have been…

Artificial Intelligence · Computer Science 2024-11-12 Xiaowei Long , Jie Lin , Xiangyuan Yang

This paper proposes an imitation learning (IL) framework for synthesizing neural network (NN) controllers that achieve boundary stabilization of systems governed by reaction-diffusion partial differential equations (PDEs). The plant is…

Optimization and Control · Mathematics 2025-11-18 Paulo Henrique Foganholo Biazetto , Mirko Fiacchini , Christophe Prieur , Gustavo Artur de Andrade

This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by…

Artificial Intelligence · Computer Science 2016-12-23 Wendelin Böhmer , Rong Guo , Klaus Obermayer

Deep Reinforcement Learning has demonstrated the potential of neural networks tuned with gradient descent for solving complex tasks in well-delimited environments. However, these neural systems are slow learners producing specialized agents…

Machine Learning · Computer Science 2022-10-13 Mathieu Chalvidal , Thomas Serre , Rufin VanRullen
‹ Prev 1 3 4 5 6 7 10 Next ›