mlsanityData to 7 Oct 2026

Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference

arXiv 2105.07693 ↗First posted 17 May 2021cs.LG cs.RO cs.SYcited by 3

Not on the map. Why?

Abstract (arXiv)

Optimal control under uncertainty is a prevailing challenge for many reasons. One of the critical difficulties lies in producing tractable solutions for the underlying stochastic optimization problem. We show how advanced approximate inference techniques can be used to handle the statistical approximations principled and practically by framing the control problem as a problem of input estimation. Analyzing the Gaussian setting, we present an inference-based solver that is effective in stochastic and deterministic settings and was found to be superior to popular baselines on nonlinear simulated tasks. We draw connections that relate this inference formulation to previous approaches for stochastic optimal control and outline several advantages that this inference view brings due to its statistical nature.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 102 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

19 of 102 references.

References · 19

  1. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
  2. 2015Probabilistic Numerics and Uncertainty in Computationscited by 59
  3. 2017Continuous-Time Gaussian Process Motion Planning via Probabilistic Inferencecited by 49
  4. 2018Variational Bayesian Reinforcement Learning with Regret Boundscited by 31
  5. 2019An Online Learning Approach to Model Predictive Controlcited by 29
  6. 2020Stein Variational Model Predictive Controlcited by 29
  7. 2015Adaptive importance sampling for control and inferencecited by 23
  8. 2014Optimal steering of a linear stochastic system to a final probability distributioncited by 22
  9. 2019From self-tuning regulators to reinforcement learning and back againcited by 17
  10. 2019Stochastic Optimal Control as Approximate Input Inferencecited by 14
  11. 2015Dual Control for Approximate Bayesian Reinforcement Learningcited by 9
  12. 2019Nonlinear Covariance Control via Differential Dynamic Programmingcited by 6
7 more
  1. 2017Finite-Horizon Covariance Control of Linear Time-Varying Systemscited by 5
  2. 2020Greedy Finite-Horizon Covariance Steering for Discrete-Time Stochastic Nonlinear Systems Based on the Unscented Transformcited by 3
  3. 2021Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Riskcited by 3
  4. 2015Risk Sensitive, Nonlinear Optimal Control: Iterative Linear Exponential-Quadratic Optimal Control with Gaussian Noisecited by 2
  5. 2017Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inferencecited by 2
  6. 2019On Approximate Nonlinear Gaussian Message Passing On Factor Graphscited by 1
  7. 2020Direct Policy Optimization using Deterministic Sampling and Collocationcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2022Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processescited by 10
  2. 2024Deterministic Trajectory Optimization through Probabilistic Optimal Controlcited by 0
  3. 2025Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspectivecited by 0