Reinforcement learning (Q2571): Difference between revisions
(Added [de] label: Reinforcement learning with human feedback - GraphIT.htm) |
(Created claim: depends on (P1): Supervised learning (Q2199)) |
||
| (7 intermediate revisions by the same user not shown) | |||
| label / en | label / en | ||
Reinforcement learning | Reinforcement learning | ||
| label / de | label / de | ||
Reinforcement learning | Reinforcement learning | ||
| description / en | description / en | ||
Successful solutions are rewarded and given greater weight | |||
| description / de | description / de | ||
Erfolgreiche Lösungsansätze werden belohnt, und später stärker gewichtet | |||
| Property / depends on | |||
| Property / depends on: Machine learning / rank | |||
Normal rank | |||
| Property / depends on | |||
| Property / depends on: Training AI models / rank | |||
Normal rank | |||
| Property / depends on | |||
| Property / depends on: Supervised learning / rank | |||
Normal rank | |||
Latest revision as of 13:42, 27 January 2026
Successful solutions are rewarded and given greater weight
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Reinforcement learning |
Successful solutions are rewarded and given greater weight |