Reinforcement learning common use cases, recommendation engine, productivity - Susan Shu Chang the data scientist show#039
The Data Scientist Show - Daliana Liu
00:00
Do You Have a Domain Knowledge?
The idea of giving rewards or a, i don't now extent, the subscription period tos typo sans, has to be feeed to the on by the data scientist. And it's not necessarely a bad thing, right, when the agent only avd at once a week, because sometimes you also don't want the obdet to be kind of too sensitive to, like, a small change. So although the agent can learn, for example, the example of giving customar rewards, watist optima amount to rewards.
Transcript
Play full episode
