Utility function security in artificially intelligent agents.
Roman V. YampolskiyPublished in: J. Exp. Theor. Artif. Intell. (2014)
Keyphrases
- intelligent agents
- utility function
- decision makers
- decision problems
- multi attribute
- decision theory
- multi agent
- multi agent systems
- intelligent systems
- building intelligent
- expected utility
- probability distribution
- risk aversion
- agent architecture
- distributed environment
- preference elicitation
- software agents
- artificial intelligence
- agent interactions
- optimization criterion
- makes sense
- quasiconvex
- knowledge base
- utility maximization
- risk averse
- decision making
- minimax regret
- social welfare
- mental states