# Model-based Path Integral Stochastic Control: A Bayesian Nonparametric Approach

arXiv: https://arxiv.org/abs/1412.3038 · HTML: https://mlsanity.com/paper/1412.3038/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2014.

## Built on by (most cited first, 2 of 2)

- [Value Iteration in Continuous Actions, States and Time](https://mlsanity.com/paper/2105.04682/) (2021)
- [Continuous-Time Fitted Value Iteration for Robust Policies](https://mlsanity.com/paper/2110.01954/) (2021)

## Abstract (arXiv)

Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics. However, such approaches require a large amount of samples from many interactions with the physical systems. To improve learning efficiency, we present a novel model-based and data-driven SOC framework based on path integral formulation and Gaussian processes (GPs). The proposed approach learns explicit and time-varying optimal controls autonomously from limited sampled data. Based on this framework, we propose an iterative control scheme with improved applicability in higher-dimensional and more complex control tasks. We demonstrate the effectiveness and efficiency of the proposed framework using two nontrivial examples. Compared to state-of-the-art RL methods, the proposed framework features superior control learning efficiency.