On the effect of the sampling ratio of past trajectories in the combination of evolutionary algorithm and deep reinforcement learning.
Yasen WangYouhei AkimotoPublished in: GECCO Companion (2022)
Keyphrases
- evolutionary algorithm
- reinforcement learning
- evolutionary computation
- multi objective
- optimization problems
- differential evolution
- multi objective optimization
- function approximation
- fitness function
- genetic programming
- genetic algorithm
- markov decision processes
- model free
- quantum evolutionary algorithm
- function optimization
- sample size
- crossover operator
- optimal control
- optimal policy
- data sets
- random sampling
- moving objects
- dynamic programming
- genetic operators
- temporal difference
- sampling algorithm
- multiple targets
- evolutionary strategy
- dynamic environments
- moving object trajectories
- robotic control