KwickClips Artificial Intelligence · 36 sec · free
How does a program learn a game with no teacher?
Short answer. Reinforcement learning.
What is the agent's goal?
Collect the most reward over time.
Reinforcement learning
| Agent takes an action |
| Reward: +10 for good moves |
| Penalty: -1 for bad moves |
Remember
| Maximise reward over time |
How does a program learn a game with no teacher? Through reinforcement learning. An agent takes actions. Good moves earn rewards. Bad moves get penalties. The agent tries to collect the most reward.
This clip is from the full lesson: Types of Machine Learning: Supervised, Unsupervised and Reinforcement — 6 minutes, with the tables, the quick answers and the whole lesson in text.
Useful for: CBSE Class 10 Artificial Intelligence (417), CBSE Class 11 Artificial Intelligence (843), CBSE Class 11 Artificial Intelligence (843), CBSE Class 11 Artificial Intelligence (843)
More KwickClips from this lesson
How does a spam filter know what spam is?35 sec
Can a model learn with no labels?39 sec
Example of unsupervised learning?39 secVoice-over is AI-generated; the script is written and checked by Kajal Ma'am. Confirm anything you plan around against your official board document. We never ask for a password or an OTP.