Honesty Is the Best Policy: Defining and Mitigating AI Deception.
Francis Rhys WardFrancesco BelardinelliFrancesca ToniTom EverittPublished in: CoRR (2023)
Keyphrases
- artificial intelligence
- machine learning
- expert systems
- optimal policy
- case based reasoning
- intelligent systems
- knowledge representation
- john mccarthy
- cognitive processes
- incomplete information
- knowledge based systems
- mental states
- knowledge representation and reasoning
- ai community
- sufficient conditions
- computational intelligence
- decision making
- risk management
- decision process
- information systems
- markov decision process
- ai methods
- data mining