Arguments about Highly Reliable Agent Designs as a Useful Path to Artificial Intelligence Safety.
Issa RiceDavid ManheimPublished in: CoRR (2022)
Keyphrases
- highly reliable
- artificial intelligence
- intelligent agents
- practical reasoning
- multi agent
- multi agent systems
- multiagent systems
- decision making
- autonomous agents
- intelligent behavior
- agent model
- expert systems
- agent architecture
- shortest path
- intelligent systems
- mobile agents
- artificial agents
- agent systems
- computational intelligence
- action selection
- decision theoretic
- multiple agents
- social simulation
- argumentation systems
- machine learning
- pedagogical agents
- engineering design
- software agents
- knowledge representation
- computer science
- design space
- cognitive science
- social welfare
- end to end
- knowledge based systems
- natural language processing
- goal state
- general game playing