Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization

• URL: http://arxiv.org/abs/2509.14848v1
• Date: Thu, 18 Sep 2025 11:12:22 GMT
• Title: Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization
• Authors: Houssem Sifaou, Osvaldo Simeone,
• Abstract summary: We introduce multi-fidelity hybrid RL via information gain (MFHRL-IGM)<n>MFHRL-IGM is a hybrid offline-online RL algorithm that implements fidelity selection based on information gain through a bootstrapping approach.
• Score: 34.31568550964209
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimizing a reinforcement learning (RL) policy typically requires extensive interactions with a high-fidelity simulator of the environment, which are often costly or impractical. Offline RL addresses this problem by allowing training from pre-collected data, but its effectiveness is strongly constrained by the size and quality of the dataset. Hybrid offline-online RL leverages both offline data and interactions with a single simulator of the environment. In many real-world scenarios, however, multiple simulators with varying levels of fidelity and computational cost are available. In this work, we study multi-fidelity hybrid RL for policy optimization under a fixed cost budget. We introduce multi-fidelity hybrid RL via information gain maximization (MF-HRL-IGM), a hybrid offline-online RL algorithm that implements fidelity selection based on information gain maximization through a bootstrapping approach. Theoretical analysis establishes the no-regret property of MF-HRL-IGM, while empirical evaluations demonstrate its superior performance compared to existing benchmarks.

Related papers

• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [111.1749164063616]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• MOORL: A Framework for Integrating Offline-Online Reinforcement Learning [6.7265073544042995]
  We propose Meta Offline-Online Reinforcement Learning (MOORL), a hybrid framework that unifies offline and online learning.<n>Our theoretical analysis demonstrates that the hybrid approach enhances exploration by effectively combining the complementary strengths of offline and online data.<n>With minimal computational overhead, MOORL achieves strong performance, underscoring its potential for practical applications in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-11T10:12:50Z)
• Hybrid Cross-domain Robust Reinforcement Learning [26.850955692805186]
  Robust reinforcement learning (RL) aims to learn policies that remain effective despite uncertainties in its environment.<n>In this paper, we introduce HYDRO, the first Hybrid Cross-Domain Robust RL framework designed to address these challenges.<n>By measuring and minimizing performance gaps between the simulator and the worst-case models in the uncertainty set, HYDRO employs novel uncertainty filtering and prioritized sampling to select the most relevant and reliable simulator samples.
  arXiv  Detail & Related papers  (2025-05-29T02:25:13Z)
• A Benchmark Environment for Offline Reinforcement Learning in Racing Games [54.83171948184851]
  Offline Reinforcement Learning (ORL) is a promising approach to reduce the high sample complexity of traditional Reinforcement Learning (RL) This paper introduces OfflineMania, a novel environment for ORL research. It is inspired by the iconic TrackMania series and developed using the Unity 3D game engine.
  arXiv  Detail & Related papers  (2024-07-12T16:44:03Z)
• Preference Elicitation for Offline Reinforcement Learning [59.136381500967744]
  We propose Sim-OPRL, an offline preference-based reinforcement learning algorithm.<n>Our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy.
  arXiv  Detail & Related papers  (2024-06-26T15:59:13Z)
• H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps [30.590370256557012]
  We develop a new algorithm, called H2O+, which offers great flexibility to bridge various choices of offline and online learning methods.<n>We demonstrate superior performance and flexibility over advanced cross-domain online and offline RL algorithms.
  arXiv  Detail & Related papers  (2023-09-22T08:58:22Z)
• Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning [66.43003402281659]
  A central question boils down to how to efficiently utilize online data collection to strengthen and complement the offline dataset. We design a three-stage hybrid RL algorithm that beats the best of both worlds -- pure offline RL and pure online RL. The proposed algorithm does not require any reward information during data collection.
  arXiv  Detail & Related papers  (2023-05-17T15:17:23Z)
• Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient [42.47810044648846]
  We consider a hybrid reinforcement learning setting (Hybrid RL) in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction. We adapt the classical Q learning/iteration algorithm to the hybrid setting, which we call Hybrid Q-Learning or Hy-Q. We show that Hy-Q with neural network function approximation outperforms state-of-the-art online, offline, and hybrid RL baselines on challenging benchmarks.
  arXiv  Detail & Related papers  (2022-10-13T04:19:05Z)
• Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL [82.93243616342275]
  We introduce Offline Model-based RL with Adaptive Behavioral Priors (MABE) MABE is based on the finding that dynamics models, which support within-domain generalization, and behavioral priors, which support cross-domain generalization, are complementary. In experiments that require cross-domain generalization, we find that MABE outperforms prior methods.
  arXiv  Detail & Related papers  (2021-06-16T20:48:49Z)
• Critic Regularized Regression [70.8487887738354]
  We propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR) We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces.
  arXiv  Detail & Related papers  (2020-06-26T17:50:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.