hAIgopala › AI terms › How Bit Really Learns › Day 8

Reinforcement Learning (RL)

Learning TypesChapter 1: Learning from EnquiriesTerm 26 of 253

Agent learns by trial and error, receiving rewards or penalties for actions.

At Sunrise School

Gopal asks

Can Bit improve from parents' feedback?

Bit answers

Reinforcement learning: a thumbs-up is a reward, a thumbs-down a penalty. Over time I prefer the replies that earn rewards.

In the real world

Training a dog with treats; AlphaGo.

Watch the short

Short coming soonSeason 2 · Day 8Follow @haigopala

Quick check

Quick check. Is a thumbs-down useful for learning? Yes or no?

Practise it

Try this term and all 253 others in the free Model Training Arena.

Open the Arena →

Follow Bit daily: YouTube English · తెలుగు · हिंदी  |  Instagram English · తెలుగు · हिंदी