# Path Integral Networks: End-to-End Differentiable Optimal Control

arXiv: https://arxiv.org/abs/1706.09597 · HTML: https://mlsanity.com/paper/1706.09597/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 16 of 16)

- [DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles](https://mlsanity.com/paper/2212.06437/) (2022)
- [Mismatched No More: Joint Model-Policy Optimization for Model-Based RL](https://mlsanity.com/paper/2110.02758/) (2021)
- [Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation](https://mlsanity.com/paper/2105.07593/) (2021)
- [Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective](https://mlsanity.com/paper/2209.08466/) (2022)
- [Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems](https://mlsanity.com/paper/2306.13867/) (2023)
- [Learning to Optimize in Model Predictive Control](https://mlsanity.com/paper/2212.02603/) (2022)
- [Learning Sampling Distributions for Model Predictive Control](https://mlsanity.com/paper/2212.02587/) (2022)
- [Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning](https://mlsanity.com/paper/2405.17031/) (2024)
- [A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2310.06253/) (2023)
- [Domain-Adversarial and Conditional State Space Model for Imitation Learning](https://mlsanity.com/paper/2001.11628/) (2020)
- [Deep Model Predictive Optimization](https://mlsanity.com/paper/2310.04590/) (2023)
- [Model-based Reinforcement Learning with Multi-step Plan Value Estimation](https://mlsanity.com/paper/2209.05530/) (2022)
- [Myriad: a real-world testbed to bridge trajectory optimization and deep learning](https://mlsanity.com/paper/2202.10600/) (2022)
- [Learning Stability Attention in Vision-based End-to-end Driving Policies](https://mlsanity.com/paper/2304.02733/) (2023)
- [Online Control-Informed Learning](https://mlsanity.com/paper/2410.03924/) (2024)
- [DiffCoord: Differentiable Coordination for Distributed Multi-Agent Trajectory Optimization](https://mlsanity.com/paper/2509.01630/) (2025)

## Abstract (arXiv)

In this paper, we introduce Path Integral Networks (PI-Net), a recurrent network representation of the Path Integral optimal control algorithm. The network includes both system dynamics and cost models, used for optimal control based planning. PI-Net is fully differentiable, learning both dynamics and cost models end-to-end by back-propagation and stochastic gradient descent. Because of this, PI-Net can learn to plan. PI-Net has several advantages: it can generalize to unseen states thanks to planning, it can be applied to continuous control tasks, and it allows for a wide variety learning schemes, including imitation and reinforcement learning. Preliminary experiment results show that PI-Net, trained by imitation learning, can mimic control demonstrations for two simulated problems; a linear system and a pendulum swing-up problem. We also show that PI-Net is able to learn dynamics and cost models latent in the demonstrations.