A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark.
Thomas CassimonReinout EyckermanSiegfried MercelisSteven LatréPeter HellinckxPublished in: CoRR (2021)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- function approximation
- reinforcement learning algorithms
- objective function
- state space
- multi objective optimization problems
- genetic algorithm
- multiobjective optimization
- multiple objectives
- optimal policy
- particle swarm optimization
- evolutionary optimization
- nsga ii
- robotic control
- machine learning
- evolutionary computation
- conflicting objectives
- optimization problems
- dynamic programming
- comparative analysis
- multi objective evolutionary algorithms
- bi objective
- model free
- learning algorithm
- optimal control
- online reviews
- multi criteria
- real world
- markov decision processes
- temporal difference
- pareto optimal
- function approximators
- learning problems
- genetic programming
- transition model
- policy search
- multi objective problems
- case study
- multi objective evolutionary