Evolutionary Computation and AI Safety: Research Problems Impeding Routine and Safe Real-world Application of Evolution
arXiv:1906.10189
Abstract
Recent developments in artificial intelligence and machine learning have spurred interest in the growing field of AI safety, which studies how to prevent human-harming accidents when deploying AI systems. This paper thus explores the intersection of AI safety with evolutionary computation, to show how safety issues arise in evolutionary computation and how understanding from evolutionary computational and biological evolution can inform the broader study of AI safety.
References in corpus (13)
- Robust Physical-World Attacks on Deep Learning Models
- A Study on Overfitting in Deep Reinforcement Learning
- Uncertainty-Aware Reinforcement Learning for Collision Avoidance
- Quantifying Generalization in Reinforcement Learning
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
- Scalable agent alignment via reward modeling: a research direction
- AI Safety Gridworlds
- Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
- Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
- AI safety via debate
- Supervising strong learners by amplifying weak experts
- Low Impact Artificial Intelligences