Modular Multi-Objective Deep Reinforcement Learning with Decision Values.
Tomasz TajmajerPublished in: FedCSIS (2018)
Keyphrases
- multi objective
- reinforcement learning
- multi objective optimization
- decision making
- evolutionary algorithm
- optimization algorithm
- genetic algorithm
- state space
- multiobjective optimization
- multiple objectives
- objective function
- decision rules
- nsga ii
- decision problems
- function approximation
- conflicting objectives
- multi objective optimization problems
- robotic control
- learning algorithm
- parameter values
- decision process
- markov decision processes
- particle swarm optimization
- pareto optimal
- temporal difference
- reinforcement learning algorithms
- simulated annealing
- evolutionary optimization
- trade off
- multi agent