Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Дълбоко обучение с подкрепление× | Цялочислено оптимиране× | |
|---|---|---|
| Област≠ | Дълбоко обучение | Оптимизация |
| Семейство≠ | Machine learning | Process / pipeline |
| Година на възникване≠ | 2015 | 1958 |
| Създател≠ | Mnih, V. et al. (DQN) | Ralph Gomory (cutting planes, 1958); land-and-doig branch-and-bound (1960) |
| Тип≠ | Sequential decision-making (agent–environment interaction) | Mathematical optimisation — exact combinatorial method |
| Основополагащ източник≠ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ | Wolsey, L.A. (1998). Integer Programming. Wiley. ISBN: 9780471283669 |
| Други названия≠ | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL | IP, MIP, mixed-integer programming, mixed-integer linear programming |
| Свързани | 4 | 4 |
| Резюме≠ | 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. | Integer programming (IP), also called mixed-integer programming (MIP) when only some variables are restricted to whole numbers, is a branch of mathematical optimisation in which some or all decision variables must take integer or binary values. Building on linear programming, it was formalised through Ralph Gomory's cutting-plane method (1958) and the Land-and-Doig branch-and-bound algorithm (1960), and it has since become the standard exact framework for scheduling, assignment, routing, and resource-allocation problems. |
| ScholarGateНабор от данни ↗ |
|
|