English
Related papers

Related papers: PFPN: Continuous Control of Physically Simulated C…

200 papers

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Machine Learning · Computer Science 2023-11-07 Tyler Westenbroek , Jacob Levy , David Fridovich-Keil

Model-based feedforward control improves tracking performance of motion systems, provided that the model describing the inverse dynamics is of sufficient accuracy. Model sets, such as neural networks (NNs) and physics-guided neural networks…

Systems and Control · Electrical Eng. & Systems 2022-04-04 Max Bolderman , Mircea Lazar , Hans Butler

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn…

Graphics · Computer Science 2023-05-08 Pei Xu , Xiumin Shang , Victor Zordan , Ioannis Karamouzas

Actor-critic algorithms that make use of distributional policy evaluation have frequently been shown to outperform their non-distributional counterparts on many challenging control tasks. Examples of this behavior include the D4PG and DMPO…

Particle dynamics and multi-agent systems provide accurate dynamical models for studying and forecasting the behavior of complex interacting systems. They often take the form of a high-dimensional system of differential equations…

Machine Learning · Computer Science 2023-08-09 Yuxuan Liu , Scott G. McCalla , Hayden Schaeffer

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our…

Machine Learning · Statistics 2019-12-03 Kyriakos Polymenakos , Alessandro Abate , Stephen Roberts

Safety-critical applications require controllers/policies that can guarantee safety with high confidence. The control barrier function is a useful tool to guarantee safety if we have access to the ground-truth system dynamics. In practice,…

Machine Learning · Computer Science 2021-12-30 Athindran Ramesh Kumar , Sulin Liu , Jaime F. Fisac , Ryan P. Adams , Peter J. Ramadge

Substitution of well-grounded theoretical models by data-driven predictions is not as simple in engineering and sciences as it is in social and economic fields. Scientific problems suffer most times from paucity of data, while they may…

Machine Learning · Computer Science 2020-11-18 Jacobo Ayensa-Jiménez , Mohamed H. Doweidar , Jose Antonio Sanz-Herrera , Manuel Doblaré

Learning a control policy capable of adapting to time-varying and potentially evolving system dynamics has been a great challenge to the mainstream reinforcement learning (RL). Mainly, the ever-changing system properties would continuously…

Machine Learning · Computer Science 2022-08-31 Po-Hsiang Chiu , Manfred Huber

Turbulent diffusion causes particles placed in proximity to separate. We investigate the required swimming efforts to maintain an active particle close to its passively advected counterpart. We explore optimally balancing these efforts by…

Systems and Control · Electrical Eng. & Systems 2024-11-12 Christopher Koh , Laurent Pagnier , Michael Chertkov

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Particle filtering is a popular method for inferring latent states in stochastic dynamical systems, whose theoretical properties have been well studied in machine learning and statistics communities. In many control problems, e.g.,…

Machine Learning · Computer Science 2021-07-12 Simon S. Du , Wei Hu , Zhiyuan Li , Ruoqi Shen , Zhao Song , Jiajun Wu

While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable…

Machine Learning · Statistics 2019-05-10 Ziyu Wang , Tongzheng Ren , Jun Zhu , Bo Zhang

We explore the use of policy gradient methods in reinforcement learning for quantum control via energy landscape shaping of XX-Heisenberg spin chains in a model agnostic fashion. Their performance is compared to finding controllers using…

Quantum Physics · Physics 2022-07-19 I. Khalid , C. A. Weidner , E. A. Jonckheere , S. G. Schirmer , F. C. Langbein

Robotics policies are always subjected to complex, second order dynamics that entangle their actions with resulting states. In reinforcement learning (RL) contexts, policies have the burden of deciphering these complicated interactions over…

Robotics · Computer Science 2024-05-06 Karl Van Wyk , Ankur Handa , Viktor Makoviychuk , Yijie Guo , Arthur Allshire , Nathan D. Ratliff

Accurate localization is a critical requirement for most robotic tasks. The main body of existing work is focused on passive localization in which the motions of the robot are assumed given, abstracting from their influence on sampling…

Robotics · Computer Science 2022-10-17 Daniel Honerkamp , Suresh Guttikonda , Abhinav Valada

A particle filter is introduced to numerically approximate a solution of the global optimization problem. The theoretical significance of this work comes from its variational aspects: (i) the proposed particle filter is a controlled…

Optimization and Control · Mathematics 2017-01-11 Chi Zhang , Amirhossein Taghvaei , Prashant G. Mehta

High-dimensional optimization is a critical challenge for operating large-scale scientific facilities. We apply a physics-informed Gaussian process (GP) optimizer to tune a complex system by conducting efficient global search. Typical GP…

Computational Physics · Physics 2021-07-14 Adi Hanuka , X. Huang , J. Shtalenkova , D. Kennedy , A. Edelen , V. R. Lalchand , D. Ratner , J. Duris

Humans excel in navigating diverse, complex environments with agile motor skills, exemplified by parkour practitioners performing dynamic maneuvers, such as climbing up walls and jumping across gaps. Reproducing these agile movements with…

Graphics · Computer Science 2025-05-08 Michael Xu , Yi Shi , KangKang Yin , Xue Bin Peng

Feedback particle filter (FPF) is a Monte-Carlo (MC) algorithm to approximate the solution of a stochastic filtering problem. In contrast to conventional particle filters, the Bayesian update step in FPF is implemented via a mean-field type…

Systems and Control · Electrical Eng. & Systems 2021-02-23 Amirhossein Taghvaei , Prashant G. Mehta