2 results found Sort:
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.
control-systems
motion-planning
optimal-control
control-learning
learning-control
dynamical-systems
imitation-learning
end-to-end-learning
system-identification
reinforcement-learning
trajectory-optimisation
trajectory-optimization
differentiable-programming
pontryagin-maximum-principle
inverse-reinforcement-learning
reinforcement-learning-environments
Created
2020-01-01
36 commits to master branch, last one about a year ago
PyDiffGame is a Python implementation of a Nash Equilibrium solution to Differential Games, based on a reduction of Game Hamilton-Bellman-Jacobi (GHJB) equations to Game Algebraic and Differential Ric...
quadrotor
game-theory
hamiltonian
control-theory
bellman-equation
computer-science
matrix-equations
nash-equilibrium
riccati-equation
differential-game
dynamical-systems
inverted-pendulum
numerical-methods
differential-equations
hamilton-jacobi-bellman
optimization-algorithms
object-oriented-programming
multi-objective-optimization
pontryagin-maximum-principle
artificial-intelligence-algorithms
Created
2020-04-22
323 commits to master branch, last one 10 months ago