samholt/NeuralLaplaceControl
Neural Laplace Control for Continuous-time Delayed Systems - an offline RL method combining Neural Laplace dynamics model and MPC planner to achieve near-expert policy performance in environments with irregular time intervals and an unknown constant delay.
This project offers an implementation for controlling systems with continuous, real-time dynamics, especially when there are unknown, constant delays in feedback and irregular observation times. It takes data from such systems and outputs optimized control policies. This tool is designed for researchers and engineers working with complex, time-sensitive control problems.
No commits in the last 6 months.
Use this if you are a researcher or advanced practitioner developing sophisticated control policies for systems where delays and irregular data are significant challenges.
Not ideal if you are looking for a plug-and-play solution for standard industrial control or if your system dynamics are simple and well-understood without significant delays.
Stars
16
Forks
5
Language
Python
License
MIT
Category
Last pushed
Apr 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/samholt/NeuralLaplaceControl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
cbfinn/gps
Guided Policy Search