mlsanityData to 14 Oct 2026

Hybrid Reinforcement Learning Framework for Mixed-Variable Problems

arXiv 2405.20500 ↗First posted 30 May 2024math.OC cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

Optimization problems characterized by both discrete and continuous variables are common across various disciplines, presenting unique challenges due to their complex solution landscapes and the difficulty of navigating mixed-variable spaces effectively. To Address these challenges, we introduce a hybrid Reinforcement Learning (RL) framework that synergizes RL for discrete variable selection with Bayesian Optimization for continuous variable adjustment. This framework stands out by its strategic integration of RL and continuous optimization techniques, enabling it to dynamically adapt to the problem's mixed-variable nature. By employing RL for exploring discrete decision spaces and Bayesian Optimization to refine continuous parameters, our approach not only demonstrates flexibility but also enhances optimization performance. Our experiments on synthetic functions and real-world machine learning hyperparameter tuning tasks reveal that our method consistently outperforms traditional RL, random search, and standalone Bayesian optimization in terms of effectiveness and efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 33 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

5 of 33 references.

References · 5

  1. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 236
  2. 2019A Survey of Optimization Methods from a Machine Learning Perspectivecited by 91
  3. 2019An ADMM Based Framework for AutoML Pipeline Configurationcited by 47
  4. 2020Continuous-Discrete Reinforcement Learning for Hybrid Control in Roboticscited by 44
  5. 2020Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chainscited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
  2. 2025Reconciling Discrete-Time Mixed Policies and Continuous-Time Relaxed Controls in Reinforcement Learning and Stochastic Control
  3. 2024Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs
  4. 2026Mathematical methods of reinforcement learning
  5. 2023Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
  6. 2024Combining Automated Optimisation of Hyperparameters and Reward Shape
  7. 2025Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization
  8. 2024Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives