An AI system is composed of an agent and its environment. The agents act in their environment. The environment may contain other agents.
An agent is anything that can perceive its environment through sensors and acts upon that environment through effectors.
What is Angent & Environment ??
- human agent has sensory organs such as eyes, ears, nose, tongue and skin parallel to the sensors, and other organs such as hands, legs, mouth, for effectors.
- A robotic agent replaces cameras and infrared range finders for the sensors, and various motors and actuators for effectors.
- A software agent has encoded bit strings as its programs and actions.
The Structure of Intelligent Agents
Agent’s structure can be viewed as:
- Agent = Architecture + Agent Program
- Architecture = the machinery that an agent excutes on.
- Agent Program = an implementation of an agent fu
1) Simple Reflex Agents
- They choose actions only based on the current percept.
- They are rational only if a correct decision is made only on the basis of current precept.
- Their environment is completely observable.
Condition-Action Rule – It is a rule that maps a state (condition) to an action.
2) Model-Based Reflex Agents
- They use a model of the world to choose their actions. They maintain an internal state.
- Model: knowledge about “how the things happen in the world”.
- Internal State: It is a representation of unobserved aspects of current state depending on percept history.
- Updating state requires the information about
- How the world evolves.
- How the agent’s actions affect the world
3) Goal-Based Agents
They choose their actions in order to achieve goals. Goal-based approach is more flexible than reflex agent since the knowledge supporting a decision is explicitly modeled, thereby allowing
for modifications.
- Goal: It is the description of desirable situations.
4) Utility-Based Agents
They choose actions based on a preference (utility) for each state.
Goals are inadequate when:
- There are conflicting goals only some of which can be achieved.
- Goals have some uncertainty of being achie
Agents Terminology
- Performance Measure of Agent: It is the criteria, which determines how successful an agent is.
- Behavior of Agent: It is the action that agent performs after any given sequence of percepts.
- Percept: It is agent’s perceptual inputs at a given instance.
- Percept Sequence: It is the history of all that an agent has perceived till date.
Rationality
Rationality is nothing but status of being reasonable, sensible, and having good sense of judgment.Rationality is concerned with expected actions and results depending upon what the agent has perceived. Performing actions with the aim of obtaining useful information is an important part of rationality.
What is Ideal Rational Agent?
An ideal rational agent is the one, which is capable of doing expected actions to maximize its
performance measure, on the basis of:
- Its percept sequence
- Its built-in knowledge base
Rationality of an agent depends on the following:
1. The performance measures, which determine the degree of success.
2. Agent’s Percept Sequence till now.
3. The agent’s prior knowledge about the environment.
4. The actions that the agent can carry out.
The Nature of Environments
- Some programs operate in the entirely artificial environment confined to keyboard input, database, computer file systems and character output on a screen.
- In contrast, some software agents (software robots or softbots) exist in rich, unlimited softbots domains. The simulator has a very detailed, complex environment.
- The most famous artificial environment is the Turing Test environment, in which one real and other artificial agents are tested on equal ground. This is a very challenging environment as it is highly difficult for a software agent to perform as well as a human.
Properties of Environment
The environment has multifold properties:
- Discrete / Continuous: If there are a limited number of distinct, clearly defined, states of the environment, the environment is discrete (For example, chess); otherwise it is continuous (For example, driving).
- Observable / Partially Observable: If it is possible to determine the complete state of the environment at each time point from the percepts it is observable; otherwise it is only partially observable.
- Static / Dynamic: If the environment does not change while an agent is acting, then it is static; otherwise it is dynamic.
- Single agent / Multiple agents: The environment may contain other agents which may be of the same or different kind as that of the agent.
- Accessible vs. inaccessible: If the agent’s sensory apparatus can have access to the complete state of the environment, then the environment is accessible to that agent.
- Deterministic vs. Non-deterministic: If the next state of the environment is completely determined by the current state and the actions of the agent, then the environment is deterministic; otherwise it is non-deterministic.
- Episodic vs. Non-episodic: In an episodic environment, each episode consists of the agent perceiving and then acting. The quality of its action depends just on the episode itself. Subsequent episodes do not depend on the actions in the previous episodes. Episodic environments are much simpler because the agent does not need to think ahead.
Turing test
The success of an intelligent behavior of a system can be measured with Turing Test.
Two persons and a machine to be evaluated participate in the test. Out of the two persons, one plays the role of the tester. Each of them sits in different rooms. The tester is unaware of who is machine and who is a human. He interrogates the questions by typing and sending them to both intelligences, to which he receives typed responses.
Turing test
Why Turing test is used?
The Turing test developed by Alan Turing(Computer scientist) in 1950. He proposed that “Turing test is used to determine whether or not computer(machine) can think intelligently like human”?
How Turing test works?
Alan Turing published a paper in 1950 in which he suggested an idea or a test called ‘The Imitation Game’, today known as the Turing Test. The idea behind this test was to check if machines have intelligence or not.
Turing proposed the Imitation Game where there would be two contestants, one human (of either gender) and one computer. And there would be a judge or an interrogator whose job would be to decide which of the two contestants is human and which one of them is a machine. He would do this by asking a series of questions to the contestants. Hence in this game if the accuracy of the Judge was less than 50% then it meant that he is likely to pick either of them. This would suggest that a computer is a quite good simulation of human and therefore intelligent.
Modified Turing test
The Turing test has recently been modified to one contestant which could be either human or machine and the interrogator has to make a decision for the single contestant whether the contestant is a human or machine.
At a time when Turing proposed this test, there were hardly any believers for it but if we see today around us, Artificial Intelligence does exist. In the recent time AI has garnered so much importance and every industry in their own way is trying to use AI, be it Banking or Information technology or Sports or Education.
A simplest illustration of AI being used would be apps like Siri, Cortana or Google Now. These apps are assisted by AI and have become an integral part of our everyday lives.
Limitations of Turing test
- computer might only score high if the questioner formulated the queries, so they had "Yes" or "No" answers or pertained to a narrow field of knowledge. When questions were open-ended and required conversational answers, it was less likely that the computer program could successfully fool the questioner.
- ELIZA could pass the Turing Test by manipulating symbols it does not understand fully. John Searle argued that this does not determine intelligence comparable to humans.
- Instead of focusing on how to convince someone they are conversing with a human and not a computer program, the real focus should be on how to make a human machine interaction more intuitive and efficient
Variations and alternatives to the Turing Test
Variations
Reverse Turing Test- Where a human tries to convince a computer that it is not a computer.
- Total Turing Test- Where the questioner can also test perceptual abilities as well as the ability to manipulate objects.
- Minimum Intelligent Signal Test- Where only true/false and yes/no questions are given.
Alternative
- The Marcus Test- In which a program which can ‘watch’ a television show is tested by being asked meaningful questions about the show's content.
- The Lovelace Test 2.0- Which is a test made to detect AI through examining its ability to create art.
- Winograd Schema Challenge- Which is a test that asks multiple-choice questions in a specific format.
Why Turing test important ??
Turing has influenced how we view AI ever since – the Turing Test has often been held up as a vital threshold AI must pass en route to true intelligence. If an AI machine could fool people into believing it is human in conversation, he proposed, then it would have reached an important milestone.
Turing test synthesis :
- Participants
- Actor A: A human evaluator
- Actor B: Another human
- Actor C: The machine you want to test
- Setting
- The participants are separated
- The conversation has to take place on text-only channels, like screen and keyboard
- The evaluator knows in advance that either (B) or (C) is a machine, but he does not know which one
- The test
- The evaluator (A) can have a conversation with (B) or (C)
- The evaluator has to reliably tell the machine from the human. If he can’t, the machine has passed the test!
since its inception, the Turing test has been highly influential. It is the most famous concept in the philosophy of artificial intelligence. You can find out more on Wikipedia.
Comments
Post a Comment