Envy-free Policy Teaching to Multiple Agents.
Jiarui GanRupak MajumdarAdish SinglaGoran RadanovicPublished in: NeurIPS (2022)
Keyphrases
- multiple agents
- reward function
- multi agent
- envy free
- single agent
- multi agent coordination
- e learning
- genetic algorithm
- optimal policy
- pareto optimal
- multi objective
- preference relations
- genetic programming
- particle swarm optimization
- sufficient conditions
- np hard
- decision problems
- lower bound
- computational complexity
- preference elicitation
- cooperative
- neural network