Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Duboko pojačavajuće učenje× | Slučajna šuma× | |
|---|---|---|
| Područje≠ | Duboko učenje | Strojno učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2015 | 2001 |
| Tvorac≠ | Mnih, V. et al. (DQN) | Breiman, L. |
| Vrsta≠ | Sequential decision-making (agent–environment interaction) | Ensemble (bagging of decision trees) |
| Temeljni izvor≠ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ |
| Drugi nazivi≠ | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble |
| Srodne | 4 | 4 |
| Sažetak≠ | 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. | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. |
| ScholarGateSkup podataka ↗ |
|
|