DeepAI AI Chat
Log In Sign Up

Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework

by   Wanxin Jin, et al.

This paper develops a Pontryagin differentiable programming (PDP) methodology to establish a unified end-to-end learning framework, which solves a large class of learning and control tasks. The proposed PDP framework distinguishes itself from existing ones by two key techniques: first, by differentiating the Pontryagin's Maximum Principle, the PDP framework allows for an end-to-end learning of any parameterized system, even though differentiation with respect to an unknown objective function is not readily attainable; and second, based on control theory, the PDP framework incorporates both the forward and backward propagations by constructing two separate control systems, which are then efficiently solved using techniques in control domain. Three learning modes of the proposed PDP framework are investigated to address three types of learning problems: inverse optimization, system identification, and control/planing, respectively. Effectiveness of this framework in each learning mode has been validated in the context of pendulum systems.


page 1

page 2

page 3

page 4


Flexible Differentiable Optimization via Model Transformations

We introduce DiffOpt.jl, a Julia library to differentiate through the so...

Topology Optimization through Differentiable Finite Element Solver

In this paper, a topology optimization framework utilizing automatic dif...

Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs

This paper introduces a new formulation for stochastic optimal control a...

Learning with Differentiable Perturbed Optimizers

Machine learning pipelines often rely on optimization procedures to make...

Certifiable Robot Design Optimization using Differentiable Programming

There is a growing need for computational tools to automatically design ...

End-to-End Learning and Intervention in Games

In a social system, the self-interest of agents can be detrimental to th...

Neural Lyapunov Differentiable Predictive Control

We present a learning-based predictive control methodology using the dif...