ALPHA adaptively selects among non-hierarchical low-fidelity models during reinforcement learning, using policy alignment with the high-fidelity policy to train a high-quality design policy.
Reinforcement Learning for Efficient Design Space Exploration With Variable Fidelity Analysis Models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment
ALPHA adaptively selects among non-hierarchical low-fidelity models during reinforcement learning, using policy alignment with the high-fidelity policy to train a high-quality design policy.