# Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulation

arXiv: https://arxiv.org/abs/2103.16432 · HTML: https://mlsanity.com/paper/2103.16432/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2021.

## Built on by (most cited first, 5 of 5)

- [Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System](https://mlsanity.com/paper/2112.04219/) (2021)
- [Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach](https://mlsanity.com/paper/2112.09046/) (2021)
- [Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systems](https://mlsanity.com/paper/2403.00381/) (2024)
- [MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management](https://mlsanity.com/paper/2502.07280/) (2025)
- [MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Control](https://mlsanity.com/paper/2512.24955/) (2025)

## Abstract (arXiv)

Deep reinforcement learning (DRL) has been successfully used to solve various robotic manipulation tasks. However, most of the existing works do not address the issue of control stability. This is in sharp contrast to the control theory community where the well-established norm is to prove stability whenever a control law is synthesized. What makes traditional stability analysis difficult for DRL are the uninterpretable nature of the neural network policies and unknown system dynamics. In this work, stability is obtained by deriving an interpretable deep policy structure based on the textitenergy shaping control of Lagrangian systems. Then, stability during physical interaction with an unknown environment is established based on textitpassivity. The result is a stability guaranteeing DRL in a model-free framework that is general enough for contact-rich manipulation tasks. With an experiment on a peg-in-hole task, we demonstrate, to the best of our knowledge, the first DRL with stability guarantee on a real robotic manipulator.