Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading.
Federico CornalbaConstantin DisselkampDavide ScassolaChristopher HelfPublished in: Neural Comput. Appl. (2024)
Keyphrases
- reinforcement learning
- multi objective
- state space
- multi objective optimization
- function approximation
- financial markets
- evolutionary algorithm
- optimal control
- electronic commerce
- learning algorithm
- neural network
- conflicting objectives
- temporal difference
- model free
- eligibility traces
- multiple objectives
- machine learning
- optimization algorithm
- multi agent
- objective function
- nsga ii
- learning problems
- pareto optimal
- particle swarm optimization
- learning process
- partially observable