Multi-objective deep inverse reinforcement learning for weight estimation of objectives.
Naoya TakayamaSachiyo AraiPublished in: Artif. Life Robotics (2022)
Keyphrases
- multi objective
- inverse reinforcement learning
- multiple objectives
- conflicting objectives
- evolutionary algorithm
- multi objective optimization
- multi objective evolutionary algorithms
- bayesian nonparametric
- partially observable environments
- pareto optimal
- particle swarm optimization
- objective function
- genetic algorithm
- nsga ii
- preference elicitation
- reward function
- privacy preserving