Intro to AI 2 final terms (Lecture Reinforcement Learning)

Reinforcement Learning

Learning through interaction with an environment by receiving rewards.

Agent

An entity that learns and makes decisions in an environment.

Environment

The world with which the agent interacts.

State

A representation of the agent’s situation.

Action

A choice made by the agent.

Reward

Feedback signal used to evaluate the result of an action.

Policy

A strategy that maps states to actions.

Trajectory

A sequence of states, actions, and rewards.

Episode

A complete run of interaction from start to termination.

Markov Property

The principle that the next state depends only on the current state.

Exploration

Trying new actions to discover better strategies.

Exploitation

Choosing the best-known action to maximize reward.

Credit Assignment

Figuring out which actions led to which outcomes.