anassinator/pddp
WIP implementation of Probabilistic Differential Dynamic Programming in PyTorch
This project offers a framework for optimizing the movement paths of systems where the underlying mechanics are not fully understood. It takes in observational data about a system's behavior and aims to predict the best sequence of actions to achieve a desired outcome. This would be used by researchers and engineers working with complex robotic systems, autonomous vehicles, or other dynamic systems where precise control is challenging due to unknown factors.
No commits in the last 6 months.
Use this if you need to optimize the trajectory of a system with uncertain or partially unknown internal workings, relying on data to inform the control strategy.
Not ideal if your system's dynamics are perfectly known and can be modeled deterministically, or if you require immediate, production-ready solutions as this is a work in progress.
Stars
16
Forks
4
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anassinator/pddp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild