Log In Sign Up

Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems

by   Sandhya Saisubramanian, et al.

Autonomous agents acting in the real-world often operate based on models that ignore certain aspects of the environment. The incompleteness of any given model—handcrafted or machine acquired—is inevitable due to practical limitations of any modeling technique for complex real-world settings. Due to the limited fidelity of its model, an agent's actions may have unexpected, undesirable consequences during execution. Learning to recognize and avoid such negative side effects of the agent's actions is critical to improving the safety and reliability of autonomous systems. This emerging research topic is attracting increased attention due to the increased deployment of AI systems and their broad societal impacts. This article provides a comprehensive overview of different forms of negative side effects and the recent research efforts to address them. We identify key characteristics of negative side effects, highlight the challenges in avoiding negative side effects, and discuss recently developed approaches, contrasting their benefits and limitations. We conclude with a discussion of open questions and suggestions for future research directions.


Concrete Problems in AI Safety

Rapid progress in machine learning and artificial intelligence (AI) has ...

TanksWorld: A Multi-Agent Environment for AI Safety Research

The ability to create artificial intelligence (AI) capable of performing...

The Peril of Artificial Intelligence

— The integration of AI technology is with the hope of reducing human er...

Evaluating Temporal Observation-Based Causal Discovery Techniques Applied to Road Driver Behaviour

Autonomous robots are required to reason about the behaviour of dynamic ...

Mitigating Negative Side Effects via Environment Shaping

Agents operating in unstructured environments often produce negative sid...

Nine Potential Pitfalls when Designing Human-AI Co-Creative Systems

This position paper examines potential pitfalls on the way towards achie...

Practical Insights of Repairing Model Problems on Image Classification

Additional training of a deep learning model can cause negative effects ...