A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks

Abstract

The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification. While there are numerous efforts to develop paradigms and standard procedures to validate models, difficulties may arise due to the sequential, manual and often biased nature of the commonly adopted calibration and validation processes, thus slowing down data collections, hampering the progress towards discovering new physics, increasing expenses and possibly leading to misinterpretations of the credibility and application ranges of proposed models. This work attempts to introduce concepts from game theory and machine learning techniques to overcome many of these existing difficulties. We introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness, in order to improve experiment design and model robustness through competition. The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention. By capturing all possible design options of the laboratory experiments into a single decision tree, we recast the design of experiments as a game of combinatorial moves that can be resolved through deep reinforcement learning by the two competing players. Our adversarial framework emulates idealized scientific collaborations and competitions among researchers to achieve a better understanding of the application range of the learned material laws and prevent misinterpretations caused by conventional AI-based third-party validation.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Playing Atari with Deep Reinforcement Learning
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Interpolation Consistency Training for Semi-Supervised Learning
• Data-driven computational mechanics
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Robust Adversarial Reinforcement Learning
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Data Driven Computing with Noisy Material Data Sets
• Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
• Generative Adversarial Active Learning
• A Physics-Constrained Data-Driven Approach Based on Locally Convex Reconstruction for Noisy Database
• A phase field model for cohesive fracture in micropolar continua
• Learning how to Active Learn: A Deep Reinforcement Learning Approach
• Deep Active Learning for Named Entity Recognition
• A multiscale model of distributed fracture and permeability in solids in all-round compression

Cited by in corpus (7)

• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions
• An accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
• Equivariant geometric learning for digital rock physics: estimating formation factor and effective permeability tensors from Morse graph
• Sobolev training of thermodynamic-informed neural networks for smoothed elasto-plasticity models with level set hardening
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation