Download 1 - Eddie Jackson

Intro to Artificial Intelligence
Unit 1 of 22
Intelligent Agent
Perception action cycle
AI in finance
AI in robotics
AI in games
AI in medicine
AI on the web
Terminology
Poker is partially observable, stochastic, and adversarial
Examples of AI
Machine Translation – built for 50 languages
|
Intelligent Agents
An AI program is called an intelligent agent.
Properties of an intelligent agent:
•
•
•
•
interacts with an environment in a state
uses sensors to perceive its state
uses actuators to affect its state
has a function called its control policy that maps sensors to actuators
This class will deal with how an agent makes decisions that it can carry out with its actuators based
on past sensor data. The loop of environment feedback to sensors, agent decision, actuator
interaction with the environment and so on is called perception action cycle.
Applications Of Ai
Domain: environment, sensors, actuators.
Finance: market, prices or world events, trades.
Robotics: world, cameras/tactile sensors, motors.
Terminology
Environments can have different characteristics.
fully versus partially observable. An environment is called fully observable if what your agent can
sense at any point in time is completely sufficient to make the optimal decision i.e. its sensors can
see the entire state of the environment. That is in contrast to some other environments where agents
need memory to make the best decision.
deterministic or stochastic. Deterministic environment is one where your agent's actions uniquely
determine the outcome. There is no randomness.
discrete versus continuous. A discrete environment is one where you have finitely many action
choices, and finitely many things you can sense. For example, in chess there's finitely many board
positions, and finitely many things you can do.
benign versus adversarial environments. In benign environments, the environment might be
random. It might be stochastic, but it has no objective on its own that would contradict your own
objective. For example, weather is benign. Contrast this with adversarial environments, such as
many games, like chess, where your opponent is really out there to get you.
Examples of environments
•
•
•
checkers: fully observable, deterministic, discrete, adversarial
poker: partially observable, stochastic, discrete, adversarial
robot car: partially observable, stochastic, continuous, benign
AI And Uncertainty
AI is the technique of uncertainty management in computer software. AI is the discipline that you
apply when you want to know what to do when you don't know what to do.
Reasons for uncertainty
•
•
•
•
sensor limit
stochastic environment
laziness
ignorance - we don't know
Summary
•
attributes of intelligent agents: (partial observability, stochasticity, continuous spaces, and
adversarial natures)