Additional planning with multiple objectives for reinforcement learning.
Anqi PanWenjun XuLei WangHongliang RenPublished in: Knowl. Based Syst. (2020)
Keyphrases
- multiple objectives
- reinforcement learning
- multi objective
- action selection
- pareto optimal
- function approximation
- multi objective optimization
- problems involving
- knapsack problem
- planning problems
- state space
- goal programming
- shortest path problem
- bi objective
- multi objective genetic algorithm
- deterministic domains
- partially observable
- blocks world
- cutting stock problems
- learning algorithm
- evolutionary algorithm
- markov decision processes
- machine learning
- multiobjective optimization
- domain independent
- objective function
- complex domains
- temporal difference
- optimal policy
- heuristic search
- special case
- mobile robot
- multi agent
- decision variables
- decision theoretic
- conflicting objectives
- fitness function
- partial observability
- genetic algorithm
- stochastic domains
- multi objective problems
- neural network