An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments.
Kewen DingPeter VamplewCameron FoaleRichard DazeleyPublished in: CoRR (2024)
Keyphrases
- multi objective
- reinforcement learning
- direct policy search
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- stochastic approximation
- particle swarm optimization
- genetic algorithm
- multiobjective optimization
- objective function
- function approximation
- multiple objectives
- conflicting objectives
- evolutionary optimization
- dynamic environments
- pareto optimal
- learning automata
- bi objective
- multi agent environments
- control policies
- stochastic model
- complex environments
- optimum design
- robotic systems
- multi objective evolutionary
- real world
- stochastic processes
- multiobjective evolutionary algorithm
- multi objective optimization problems
- learning algorithm
- reinforcement learning methods
- model free
- multi agent
- markov decision processes
- monte carlo
- mobile robot