Path-Specific Objectives for Safer Agent Incentives.

Sebastian Farquhar Ryan Carey Tom Everitt

Published in: AAAI (2022)

Keyphrases

multiagent systems
high level
multi agent
intelligent agents
multi agent systems
autonomous agents
decision making
domain specific
data sets
mobile agents
dynamic environments
higher level
learning algorithm
real time
incomplete information
agent architecture
agent model
multiple agents
agent systems