wanxinjin/Learning-from-Directional-Corrections wanxinjin/Learning-from-Directional-Corrections

  • Stars
    star
    13
  • Rank 1,504,802 (Top 30 %)
  • Language
    Python
  • Created almost 4 years ago
  • Updated almost 3 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
wanxinjin/Learning-from-Directional-Corrections
github

wanxinjin

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A new method for a robot to learn a control objective from human user's directional corrections.

More Repositories

1

Pontryagin-Differentiable-Programming

A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.
Python
156
star
2

Safe-PDP

Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.
Python
64
star
3

Learning-from-Sparse-Demonstrations

A framework and method to jointly learn a (neural) control objective function and a time-warping function only from sparse demonstrations or waypoints.
Python
17
star
4

Task-Driven-Hybrid-Reduction

We developed a task-driven hybrid model reduction method for solving dexterous manipulation with 5 minutes of online learning.
Python
16
star
5

IOC-from-Incomplete-Trajectory-Observations

Inverse optimal control from incomplete trajectory observations, proposing the concept of the recovery matrix which provides further insights into objective learning process.
MATLAB
11
star
6

wanxinjin.github.io

JavaScript
3
star
7

IOC-for-Multiphase-Cost-Functions

A method to learn multi-phase objective functions, and the method is able to not only recover the objective function in each phase but also identify the phase transition points.
2
star
8

Neural-Certificates-Safe-Policies

1
star