Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning.
Manon FlageatBryan LimLuca GrillottiMaxime AllardSimón C. SmithAntoine CullyPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- orders of magnitude
- learning algorithm
- optimization problems
- quality measures
- model free
- high quality
- worst case
- computationally efficient
- recently developed
- times faster
- stochastic approximation
- neural network
- learning problems
- classification algorithm
- machine learning algorithms
- computational cost
- data structure