Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Диференціальна еволюція× | Глибоке навчання з підкріпленням× | |
|---|---|---|
| Галузь≠ | Оптимізація | Глибоке навчання |
| Родина≠ | Process / pipeline | Machine learning |
| Рік появи≠ | 1997 | 2015 |
| Автор методу≠ | Rainer Storn & Kenneth Price | Mnih, V. et al. (DQN) |
| Тип≠ | Population-based stochastic metaheuristic | Sequential decision-making (agent–environment interaction) |
| Основоположне джерело≠ | Storn, R. & Price, K. (1997). Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces. Journal of Global Optimization, 11(4), 341–359. DOI ↗ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ |
| Інші назви≠ | DE algorithm, Diferansiyel Evrim (DE), DE optimization | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL |
| Пов'язані≠ | 5 | 4 |
| Підсумок≠ | Differential Evolution (DE), introduced by Rainer Storn and Kenneth Price in 1997, is a population-based stochastic optimisation algorithm designed for continuous parameter spaces. It generates candidate solutions by combining vector differences between existing population members, making it a powerful and parameter-lean alternative to Genetic Algorithms and Particle Swarm Optimisation when the search landscape is non-convex, multimodal, or poorly suited to gradient-based methods. | Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return. |
| ScholarGateНабір даних ↗ |
|
|