Reinforcement Learning

Exploration vs Exploitation

अन्वेषण बनाम उपयोग

An RL tradeoff between trying new actions and using known rewarding ones.

Q-Learning

क्यू-लर्निङ

A reinforcement learning algorithm that learns the value of actions in each state.

AI Agent

एआई एजेन्ट

An AI system that can plan, use tools, and take actions to achieve a goal autonomously.

Data Leakage

डाटा चुहावट

When information from outside the training set sneaks in, giving misleadingly good results.

Federated Learning

फेडरेटेड लर्निङ

Training a shared model across many devices without moving their private data to a server.

Hyperparameter

हाइपरप्यारामिटर

A configuration value set before training that controls how a model learns, like learning rate.

Learning Curve

सिकाइ वक्र

A plot showing how a model's performance changes as it sees more training data.

Online Learning

अनलाइन सिकाइ

Training a model continuously as new data arrives, one piece at a time.