Adaptive Learning Of Design Strategies Over Non-hierarchical Multi-fidelity Models Via Policy Alignment

Abstract

Multi-fidelity Reinforcement Learning (RL) frameworks significantly enhance the efficiency of engineering design by leveraging analysis models with varying levels of accuracy and computational costs. The prevailing methodologies, characterized by transfer learning, human-inspired strategies, control variate techniques, and adaptive sampling, predominantly depend on a structured hierarchy of models. However, this reliance on a model hierarchy overlooks the heterogeneous error distributions of models across the design space, extending beyond mere fidelity levels. This work proposes ALPHA (Adaptively Learned Policy with Heterogeneous Analyses), a novel multi-fidelity RL framework to efficiently learn a high-fidelity policy by adaptively leveraging an arbitrary set of non-hierarchical, heterogeneous, low-fidelity models alongside a high-fidelity model. Specifically, low-fidelity policies and their experience data are dynamically used for efficient targeted learning, guided by their alignme

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyagrawal2024adaptive

Related papers

• Adaptive Multi-fidelity Reinforcement Learning For Variance Reduction In Engineering Design Optimization (2025)0.00
• Boosting Hierarchical Reinforcement Learning With Meta-learning For Complex Task Adaptation (2024)0.00
• Explaining And Preventing Alignment Collapse In Iterative RLHF (2026)0.00
• Dynamic Policy Fusion For User Alignment Without Re-interaction (2024)0.00
• Online Robust Policy Learning In The Presence Of Unknown Adversaries (2018)0.00
• Deep Reinforcement Learning From Hierarchical Preference Design (2023)2.00
• Policy Agnostic RL: Offline RL And Online RL Fine-tuning Of Any Class And Backbone (2024)0.00
• Heterogeneity-aware Personalized Federated Learning Via Adaptive Dual-agent Reinforcement Learning (2025)0.00