mlsanityData to 7 Oct 2026

Increasing Information for Model Predictive Control with Semi-Markov Decision Processes

arXiv 2501.17256 ↗First posted 28 Jan 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent works in Learning-Based Model Predictive Control of dynamical systems show impressive sample complexity performances using criteria from Information Theory to accelerate the learning procedure. However, the sequential exploration opportunities are limited by the system local state, restraining the amount of information of the observations from the current exploration trajectory. This article resolves this limitation by introducing temporal abstraction through the framework of Semi-Markov Decision Processes. The framework increases the total information of the gathered data for a fixed sampling budget, thus reducing the sample complexity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 47 references that are in the map. First posted on arXiv 28 Jan 2025.

Builds on

15 of 47 references.

References · 15

  1. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  2. 2017Deep Reinforcement Learning that Matterscited by 727
  3. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
  4. 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 90
  5. 2021Temporal Abstraction in Reinforcement Learning with the Successor Representationcited by 52
  6. 2021Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learningcited by 51
  7. 2017Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Controlcited by 50
  8. 2017Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learningcited by 38
  9. 2021Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Informationcited by 33
  10. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  11. 2019Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learningcited by 16
  12. 2021An Experimental Design Perspective on Model-Based Reinforcement Learningcited by 16
3 more
  1. 2023Neural Laplace Control for Continuous-time Delayed Systemscited by 10
  2. 2022Exploration via Planning for Information about the Optimal Trajectorycited by 8
  3. 2022Data-driven memory-dependent abstractions of dynamical systemscited by 2

Built on by

Not cited yet.