A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimization.
Akira KitaokaRiki EtoPublished in: CoRR (2023)
Keyphrases
- multi objective optimization
- inverse reinforcement learning
- partially observable environments
- multi objective
- bayesian nonparametric
- evolutionary algorithm
- preference elicitation
- multi objective optimization problems
- reward function
- reinforcement learning
- genetic algorithm
- multiple objectives
- differential evolution
- nsga ii
- temporal difference
- pareto optimal
- multi objective genetic algorithm
- objective function
- utility function
- optimization algorithm
- multiobjective optimization
- multi objective evolutionary algorithms
- particle swarm optimization
- optimization problems
- state space