Predicting outcomes and planning interactions with the physical world are long-standing goals for machine learning. A variety of such tasks involves continuous physical systems, which can be described by partial differential equations (PDEs) with many degrees of freedom. Existing methods that aim to control the dynamic…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “physical control”
PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Networkcs.LG
PFPN uses particle filtering to improve character control in physics-based simulations.
problem Premature commitment to suboptimal actions in high-dimensional continuous control problems for articulated characters.
method Proposes a particle-based action policy using particle filtering to dynamically explore and discretize the action space.
result Demonstrates better imitation performance and robustness to external perturbations compared to Gaussian policies.
This article is concerned with learning and stochastic control in physical systems which contain unknown input signals. These unknown signals are modeled as Gaussian processes (GP) with certain parametrized covariance structures. The resulting latent force models (LFMs) can be seen as hybrid models that contain a first…
Develops scalable differentiable physics for complex object interactions.
problem Limited scalability of existing differentiable physics solvers.
method Adopting meshes for arbitrary geometry, localized collision handling, and accelerated implicit differentiation.
result Significantly reduces memory and computation requirements compared to particle-based methods.
Bayesian optimisation tackles stochastic MPC hyper-parameter tuning.
problem Fine-tuning hyper-parameters in stochastic MPC models.
method Heteroscedastic Bayesian optimisation framework.
result Framework effectively tunes hyper-parameters in control problems.
In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system, given by an ordinary differential equation (ODE), from observed state trajectories. To achieve better generalization with fewer training samples, SymODEN incorporates appropriate induct…
Physics-guided reinforcement learning optimizes swimming in turbulent flows.
problem Optimizing swimming efforts to maintain proximity in turbulent environments.
method Physics-informed actor-physicist reinforcement learning algorithm.
result Physics-informed reinforcement learning outperforms standard methods in turbulent flow control.
Physics-informed neural networks improve model accuracy and efficiency.
problem Accurate dynamic models for technical systems are hard to achieve.
method Physics-informed neural ordinary differential equations (PINODE) integrating Lagrangian mechanics.
result Hybrid model combines physical insight and data approximation.
Some simple examples from quantum physics and control theory are used to illustrate the application of the theory of Lie systems. We will show, in particular, that for certain physical models both of the corresponding classical and quantum problems can be treated in a similar way, may be up to the replacement of the in…
Physics analogies explain machine learning overfitting control.
problem Understanding and controlling overfitting in machine learning.
method Analogies from physics and biology applied to algorithmic stability and GAN models.
result Physics formulas provide insights into reducing overfitting in machine learning.
Physics models integrated into VAEs improve generative performance and extrapolation.
problem Improving generative models with interpretability and robustness.
method Physics-based latent space in VAEs with regularized learning to balance physics and neural network components.
result Generative performance and extrapolation improvements demonstrated on synthetic and real-world datasets.
Defense strategy improves controller robustness against adversarial attacks.
problem Adversarial attacks on learning-enabled controllers in CPS.
method Two-stage defense strategy treating controller and environment as black-boxes with unknown dynamics.
result Defense strategy effectively improves controller robustness in realistic control domains.
Neural Lyapunov Redesigneess.SY
Combines Lyapunov functions with controller synthesis for safe control policies.
problem Ensuring safety in controller design for nonlinear systems.
method Iterative algorithm combining Lyapunov function estimation and controller synthesis.
result Effective control policies with large safe regions are derived.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
problem Predicting time-varying hardware resource availability in control software.
method Path structured multimarginal Schrödinger bridge (MSBP) for learning stochastic resource usage.
result Guaranteed linear convergence to accurate prediction of hardware resource utilization.
Model learns Lagrangian dynamics from images for better prediction and control.
problem Lack of interpretability and applicability to high-dimensional data like images.
method Unsupervised neural network model that learns Lagrangian dynamics from images using a coordinate-aware VAE.
result Model infers interpretable Lagrangian dynamics, enabling long-term prediction and synthesis of controllers.
Physics-informed learning framework for pH systems and EB-PBC control.
problem Control of port-Hamiltonian systems from trajectory data.
method Co-learning of pH system model and EB-PBC through alternating optimization.
result Proven stability and robustness of the learned controller.
Solla discusses neural processing using statistical physics and Bayesian methods.
problem Understanding neural information processing through statistical physics.
method Bayesian inference, Gibbs description, Generalized Linear Models, dimensionality reduction.
result Connection between neural processing and statistical physics.
We introduce a method for non-uniform random number generation based on sampling a physical process in a controlled environment. We demonstrate one proof-of-concept implementation of the method that reduces the error of Monte Carlo integration of a univariate Gaussian by 1068 times while doubling the speed of the Monte…
Learning with Physical Constraintsphysics.flu-dyn
Three physics-constrained regression exercises for image velocimetry and turbulence modeling.
problem Image velocimetry and turbulence modeling challenges.
method Physics-constrained regression exercises implemented as toy problems.
result Python codes provided for all exercises.
New adversarial training method improves robustness of power system controllers.
problem Designing robust controllers for complex cyber-physical power systems.
method Adversarial training approach with fixed opponent policy.
result Adversarial trained controllers show useful preventive behaviors in the N-1 problem.
In the overview, a generic mathematical object (mapping) is introduced, and its relation to model physics parameterization is explained. Machine learning (ML) tools that can be used to emulate and/or approximate mappings are introduced. Applications of ML to emulate existing parameterizations, to develop new parameteri…
Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to g…
PhysVarMix predicts diverse urban trajectories with physics constraints.
problem Predicting complex urban agent trajectories with multiple plausible scenarios.
method Physics-informed variational mixture model combining learning and physics constraints.
result Superior performance compared to existing methods on benchmark datasets.
Survey of RL methods for control systems with time delays.
problem Time delays in cyber-physical systems degrade RL performance and stability.
method Categorizes and analyzes five major families of RL methods for time delays.
result Identifies key trade-offs and practical guidelines for selecting RL methods.
Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.
problem Sparse feedback learning with high-dimensional, hybrid, or contact-dependent dynamics.
method Introduces physics-informed inductive biases into goal-conditioned value learning.
result Contact-rich manipulation tasks degrade existing Pi-GCRL methods.
NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spacescs.LG
Framework simplifies vision-based control and goal discovery.
problem Learning proportional control from visual data.
method Introduces NewtonianVAE for proportional control and goal discovery.
result Dramatic simplification and acceleration of vision-based controllers.
Backdoor attacks on DRL-based traffic controllers cause stop-and-go waves or crashes.
problem Vulnerability of DRL-based traffic controllers to machine learning attacks.
method Developed a trigger design methodology based on traffic physics principles.
result Backdoored models can cause stop-and-go traffic waves or AV crashes when triggered.
Robot-assisted dressing offers an opportunity to benefit the lives of many people with disabilities, such as some older adults. However, robots currently lack common sense about the physical implications of their actions on people. The physical implications of dressing are complicated by non-rigid garments, which can r…
Bayesian control prepares GHZ states in Rydberg atoms.
problem Preparing non-classical states robustly for quantum sensors.
method Bayesian optimal control of trapped Rydberg atoms.
result Control pulses drive atoms into GHZ states with scalable preparation times.
Algorithm mitigates performance loss in constrained reinforcement learning with model misspecification.
problem Performance loss in reinforcement learning policies due to model misspecification in constrained control systems.
method Proposes an algorithm to handle constrained model misspecification in continuous control systems.
result Algorithm successfully mitigates performance loss in real-world reinforcement learning tasks.
New approach relaxes inductive biases of physics-inspired NNs for better performance.
problem Challenges in applying physics-inspired NNs to real-world systems.
method Examined and relaxed inductive biases of Hamiltonian NNs, improving performance on non-conservative systems.
result Improved performance on practical, non-conservative systems by relaxing inductive biases.
For this special issue, the article aims at discussing a few econophysics problems studied so far rather successfully. The following "applications" in micro-econo-physics are considered : (i) financial crashes; it is emphasized that one can distinguish between endogenous and exogenous causes; (ii) portofolio control, s…
Paper tackles DOCTR-L with SciPhy RL, solving neural PDEs from data.
problem High-dimensional optimal control with stochastic policies.
method Soft HJB equation, Neural PDEs, Physics-Informed Neural Networks.
result Reduces DOCTR-L to solving neural PDEs from data.
Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world applications, these requirements are unfeasible and additional prior knowledge on the task domain is required to overcome the resulting problems…
PINNs struggle with increasingly complex ODEs, especially when parameters control their complexity.
problem Evaluating physics-informed neural networks on complex coupled ODEs.
method Tuned benchmarks of partial differential equations and harmonic oscillators; varying network architecture and training method.
result PINNs fail to solve complex ODEs, revealing issues like insufficient capacity, poor conditioning, and high local curvature.
Paper introduces SALE for better state-action learning in RL.
problem Challenges in representation learning for low-level states in RL.
method Introduces SALE, a novel approach for learning embeddings of state-action interactions.
result TD7 algorithm significantly outperforms existing continuous control algorithms.
Paper robustifies reinforcement learning agents against action space perturbations.
problem Vulnerability of reinforcement learning agents to action space perturbations (e.g. actuator attacks).
method Adversarial training to robustify DRL agents against perturbations.
result DRL agents can be robustified against action space perturbations through adversarial training.
The paper proves index theorems for graph-based optimal control problems.
problem Optimal control problems on graphs with constraints.
method Proves Morse index theorems for a broad class of variational problems on graphs.
result Formulas compute the difference of Hessians related to different graphs or boundary conditions.
Active researches are currently being performed to incorporate the wealth of scientific knowledge into data-driven approaches (e.g., neural networks) in order to improve the latter's effectiveness. In this study, the Theory-guided Neural Network (TgNN) is proposed for deep learning of subsurface flow. In the TgNN, as s…
Research explores how interconnected systems synchronize and how to control their behavior.
problem Understanding and controlling the behavior of interconnected dynamical systems.
method Mean field games approach applied to controlled coupled oscillators.
result Developed methods to predict and influence emergent phenomena in interconnected systems.
Framework identifies discrepancies in physics models, improving sensor accuracy.
problem Model inaccuracies leading to poor control algorithms.
method Learning systematic state-space residuals and deterministic dynamical errors.
result Improved quantification of system dynamics and control algorithms.
RFC enhances humanoid control to imitate complex human motions.
problem Dynamics mismatch between humanoid models and real humans.
method Residual Force Control (RFC) augments control policies with external forces.
result RFC outperforms state-of-the-art methods in convergence speed and motion quality.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Interpretable meta-learning for physical systems reduces computational costs and improves interpretability.
problem Challenges in learning from heterogeneous experimental data.
method Affine structure learning model for multi-environment generalization.
result Proves the model can identify physical parameters and demonstrates competitive performance.
Neyman-Pearson testing improves goodness of fit in detecting new physics.
problem Detecting small anomalies in data distributions.
method Employing Neyman-Pearson strategy with a rich parametrized family of models.
result Neyman-Pearson testing is more sensitive to small departures and unbiased towards specific anomalies.
Modern physics has demonstrated that matter behaves very differently as it approaches the speed of light. This paper explores the implications of modern physics to the operation and regulation of financial markets. Information cannot move faster than the speed of light. The geographic separation of market centers means…
Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Datacs.LG
Unified framework for generating meteorological time series from text.
problem Lack of large-scale, physically grounded multimodal datasets and architectures ignoring spectral-temporal structure.
method Introduce MeteoCap-3B dataset and MTransformer model.
result State-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability.
Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been developed to model the dynamics of these complex scenes; however, relying on app…