Inverse Reinforcement Learning Approach for Elicitation of Preferences in Multi-objective Sequential Optimization.
Akiko IkenagaSachiyo AraiPublished in: ICA (2018)
Keyphrases
- preference elicitation
- inverse reinforcement learning
- multi objective
- optimization algorithm
- multi criteria
- multiple objectives
- bayesian nonparametric
- utility function
- partially observable environments
- evolutionary algorithm
- multi objective optimization
- particle swarm optimization
- preference relations
- optimization problems
- objective function
- decision theory
- genetic algorithm
- differential evolution
- pareto optimal
- dynamic systems
- decision makers
- hidden markov models
- decision making
- learning algorithm