Instilling moral value alignment by means of multi-objective reinforcement learning.
Manel Rodriguez-SotoMarc SerramiaMaite López-SánchezJuan Antonio Rodríguez-AguilarPublished in: Ethics Inf. Technol. (2022)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- multiple objectives
- multiobjective optimization
- genetic algorithm
- multi objective optimization problems
- particle swarm optimization
- reinforcement learning algorithms
- state space
- dynamic programming
- trade off
- learning algorithm
- pareto optimal
- conflicting objectives
- ontology matching
- evolutionary optimization
- multiagent evolutionary algorithm
- image alignment
- learning classifier systems
- nsga ii
- function approximation
- transfer learning
- optimal policy
- objective function