Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning.
Kewen DingPublished in: CoRR (2022)
Keyphrases
- multi objective
- decision making
- reinforcement learning
- direct policy search
- evolutionary algorithm
- decision makers
- optimization algorithm
- genetic algorithm
- multi objective optimization
- multi criteria
- action selection
- stochastic approximation
- multiobjective optimization
- conflicting objectives
- learning automata
- state space
- nsga ii
- function approximation
- monte carlo
- decision support system
- multi objective evolutionary algorithms
- markov decision processes
- bi objective
- multi agent environments
- control policies
- objective function
- multiagent evolutionary algorithm
- model free
- pareto optimal
- optimal control
- information processing
- dynamic environments
- decision support
- dynamic programming
- multiple objectives
- reinforcement learning algorithms
- machine learning
- fitness function
- optimal policy
- multi agent
- approximate dynamic programming
- multi objective optimization problems
- multi objective genetic algorithms
- genetic programming