2 papers
cs.LG2025
Adaptive Multi-Fidelity Reinforcement Learning for Variance Reduction in Engineering Design Optimization
Akash Agrawal, Christopher McComb
Multi-fidelity Reinforcement Learning (RL) frameworks efficiently utilize computational resources by integrating analysis models of varying accuracy and costs. The prevailing metho…
cs.LG2024
Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment
Akash Agrawal, Christopher McComb
Multi-fidelity Reinforcement Learning (RL) frameworks significantly enhance the efficiency of engineering design by leveraging analysis models with varying levels of accuracy and c…