Honesty Is the Best Policy: Defining and Mitigating AI Deception.
Francis WardFrancesca ToniFrancesco BelardinelliTom EverittPublished in: NeurIPS (2023)
Keyphrases
- artificial intelligence
- expert systems
- intelligent systems
- knowledge representation
- optimal policy
- machine learning
- case based reasoning
- incomplete information
- ai systems
- cognitive processes
- computational intelligence
- intelligent behavior
- artificial intelligent
- ai methods
- policy makers
- mental states
- infinite horizon
- risk management
- qualitative and quantitative
- decision problems
- sufficient conditions
- ai technologies
- ai community
- decision making