Digital Twin-Based Self-Adaptation: Value-at-Risk and Learning-to-Synchronize
<p>Digital twins enable safe experimentation and adaptation of mission-critical systems by providing replicas of complex environments. However, their reduced complexity and partial observability can cause underspecification, leading to overfitting in simulation and unstable behavior after deployment...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Book Chapter |
| Language: | English |
| Published: |
IntechOpen
2026
|
| Subjects: | |
| Online Access: | https://www.intechopen.com/chapters/1243355 |
| Tags: |
No Tags, Be the first to tag this record!
|
Similar Items: Digital Twin-Based Self-Adaptation: Value-at-Risk and Learning-to-Synchronize
- Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
- Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
- Hybrid Planning with Receding Horizon: A Case for Meta-self-awareness
- CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation
- Improving Scalability and Reward of Utility-Driven Self-Healing for Large Dynamic Architectures
- A Scalable Querying Scheme for Memory-efficient Runtime Models with History