Introduction to Artificial Intelligence Questions and Answers

Q: What is a stochastic environment?

In a stochastic environment the same action in the same state can lead to different outcomes, so the agent must reason about probabilities rather than certainties. Partial observability, static behaviour and multi-agent settings are separate dimensions, though the last is often modelled as stochastic when the other agents cannot be predicted. Identifying which dimension a difficulty belongs to determines whether probability, memory or game theory is the appropriate tool.

Q: What is a dynamic environment?

A dynamic environment does not wait for the agent, so a slow decision may be acted upon in a state that no longer exists, which forces real time constraints on the design. Chess with a clock is semidynamic, since the environment is static but the score changes with time. Stochasticity, moving obstacles and changing objectives are related but separate matters. Whether an agent may take as long as it likes is one of the most consequential facts about a task.

Q: What is a simple reflex agent?

A simple reflex agent maps the current percept directly to an action through a set of rules, with no memory and no model, which is fast and adequate only in fully observable environments. Model based agents keep internal state, goal based agents consider consequences, and learning agents improve with experience. The four form a ladder of increasing capability and cost, and choosing the simplest that suffices for the environment is the design principle.

Q: What does a model based reflex agent maintain?

The agent keeps an internal state updated by a model of how the world evolves and how its own actions affect it, which lets it act sensibly when the percept alone is insufficient. Goals belong to the next architecture up, storing every percept is neither necessary nor practical, and action distributions belong to policies. Adding just enough memory to overcome partial observability, rather than storing everything, is the design idea.

Q: What does a goal based agent do that a reflex agent does not?

A goal based agent combines its model with an explicit goal and searches or plans to find actions that bring the goal about, which makes it flexible when the goal changes. Reflex agents would need every rule rewritten. Speed is if anything worse, internal state belongs to the model based agent, and learning is a further addition. Separating knowledge of the world from the objective is what makes an agent reconfigurable rather than rebuilt.

Q: What does a utility based agent add to a goal based one?

A goal is binary, achieved or not, whereas a utility function ranks outcomes, allowing the agent to trade speed against safety or cost against quality, and to act sensibly when goals conflict or are uncertain. Multiple goals and models are handled by both, and learning is an orthogonal addition. Replacing a predicate with a number is a small change that greatly enlarges the range of situations an agent can handle sensibly.

Q: What are the four components of a learning agent?

The learning element improves the performance element using feedback from the critic, while the problem generator suggests exploratory actions that may be informative though not immediately optimal. The fourth component is easily forgotten and is what prevents an agent from becoming stuck in a locally good habit. The other lists describe hardware, decision components and a processing pipeline. An explicit place for exploration in the architecture is the design's most instructive feature.

Q: What is the role of the problem generator in a learning agent?

Left to itself the performance element would always take the action it currently believes best, and would never discover anything better, so the problem generator deliberately proposes suboptimal but informative actions. It is the architectural expression of the exploration and exploitation trade. Evaluation, goal setting and data collection are separate functions. Building exploration into the design, rather than hoping it happens, is what allows a learning system to improve beyond its starting point.

Q: What is the exploration and exploitation trade off?

An agent that always exploits its current knowledge never improves, while one that always explores never uses what it has learned, and the balance between them determines how quickly it converges on good behaviour. It appears throughout reinforcement learning, bandit problems and adaptive control. Memory, methodology and evaluation cost are separate trades. A dilemma that arises purely from acting under uncertainty is one of the most general ideas in the subject.

31.

What is a stochastic environment?

A.One that changes only when the agent takes an action in it
B.One containing several other agents whose actions cannot be predicted
C.One in which an action's outcome is not determined by the state alone
D.One in which the agent cannot observe the state completely

Answer: C

In a stochastic environment the same action in the same state can lead to different outcomes, so the agent must reason about probabilities rather than certainties. Partial observability, static behaviour and multi-agent settings are separate dimensions, though the last is often modelled as stochastic when the other agents cannot be predicted. Identifying which dimension a difficulty belongs to determines whether probability, memory or game theory is the appropriate tool.

Discuss in Forum

32.

What is a dynamic environment?

A.One in which the agent's actions have unpredictable outcomes
B.One that contains moving objects the agent must avoid
C.One in which the performance measure changes over time
D.One that can change while the agent is deliberating

Answer: D

A dynamic environment does not wait for the agent, so a slow decision may be acted upon in a state that no longer exists, which forces real time constraints on the design. Chess with a clock is semidynamic, since the environment is static but the score changes with time. Stochasticity, moving obstacles and changing objectives are related but separate matters. Whether an agent may take as long as it likes is one of the most consequential facts about a task.

Discuss in Forum

33.

What is a simple reflex agent?

A.One that acts only on the current percept using condition action rules
B.One that maintains a model of the world and updates it with each percept
C.One that considers the consequences of its actions before choosing
D.One that improves its behaviour through experience over time

Answer: A

A simple reflex agent maps the current percept directly to an action through a set of rules, with no memory and no model, which is fast and adequate only in fully observable environments. Model based agents keep internal state, goal based agents consider consequences, and learning agents improve with experience. The four form a ladder of increasing capability and cost, and choosing the simplest that suffices for the environment is the design principle.

Discuss in Forum

34.

Why does a simple reflex agent fail in a partially observable environment?

A.It cannot learn from the mistakes it makes during operation
B.The current percept alone does not determine the correct action
C.It cannot execute actions quickly enough to keep up with events
D.It has no way of representing the goals it is trying to achieve

Answer: B

If two different states produce the same percept but require different actions, a rule keyed only on the percept must choose wrongly in one of them, and no set of such rules can help. Internal state carrying a memory of previous percepts is the remedy. Speed, goals and learning are separate limitations of the architecture. Recognising when an architecture is provably inadequate, rather than merely inefficient, saves a great deal of fruitless tuning.

Discuss in Forum

35.

What does a model based reflex agent maintain?

A.A record of every percept it has ever received since starting
B.A probability distribution over all possible future actions
C.Internal state representing the part of the world it cannot see
D.A list of goals to be achieved in a specified order

Answer: C

The agent keeps an internal state updated by a model of how the world evolves and how its own actions affect it, which lets it act sensibly when the percept alone is insufficient. Goals belong to the next architecture up, storing every percept is neither necessary nor practical, and action distributions belong to policies. Adding just enough memory to overcome partial observability, rather than storing everything, is the design idea.

Discuss in Forum

36.

What does a goal based agent do that a reflex agent does not?

A.Respond more quickly to changes in its immediate surroundings
B.Maintain an internal model of the unobserved parts of the world
C.Improve its performance through experience of the environment
D.Consider whether an action leads towards a desired situation

Answer: D

A goal based agent combines its model with an explicit goal and searches or plans to find actions that bring the goal about, which makes it flexible when the goal changes. Reflex agents would need every rule rewritten. Speed is if anything worse, internal state belongs to the model based agent, and learning is a further addition. Separating knowledge of the world from the objective is what makes an agent reconfigurable rather than rebuilt.

Discuss in Forum

37.

What does a utility based agent add to a goal based one?

A.A measure of how desirable each outcome is, not merely whether it satisfies
B.The ability to pursue several goals simultaneously without conflict
C.A model of the environment that the goal based agent lacks
D.The capacity to learn which goals are worth pursuing at all

Answer: A

A goal is binary, achieved or not, whereas a utility function ranks outcomes, allowing the agent to trade speed against safety or cost against quality, and to act sensibly when goals conflict or are uncertain. Multiple goals and models are handled by both, and learning is an orthogonal addition. Replacing a predicate with a number is a small change that greatly enlarges the range of situations an agent can handle sensibly.

Discuss in Forum

38.

What are the four components of a learning agent?

A.Perception, reasoning, planning and execution
B.Learning element, performance element, critic and problem generator
C.Sensors, actuators, memory and processor
D.Model, goal, utility function and policy

Answer: B

The learning element improves the performance element using feedback from the critic, while the problem generator suggests exploratory actions that may be informative though not immediately optimal. The fourth component is easily forgotten and is what prevents an agent from becoming stuck in a locally good habit. The other lists describe hardware, decision components and a processing pipeline. An explicit place for exploration in the architecture is the design's most instructive feature.

Discuss in Forum

39.

What is the role of the problem generator in a learning agent?

A.Generating the goals the agent will attempt to achieve next
B.Producing the training data from which the agent learns its model
C.Suggesting exploratory actions that may yield useful experience
D.Creating the test problems used to evaluate the agent's performance

Answer: C

Left to itself the performance element would always take the action it currently believes best, and would never discover anything better, so the problem generator deliberately proposes suboptimal but informative actions. It is the architectural expression of the exploration and exploitation trade. Evaluation, goal setting and data collection are separate functions. Building exploration into the design, rather than hoping it happens, is what allows a learning system to improve beyond its starting point.

Discuss in Forum

40.

What is the exploration and exploitation trade off?

A.Choosing between searching a state space and storing it in memory
B.Choosing between symbolic and statistical methods for a problem
C.Choosing between accuracy and speed in evaluating a position
D.Choosing between the best known action and one that may prove better

Answer: D

An agent that always exploits its current knowledge never improves, while one that always explores never uses what it has learned, and the balance between them determines how quickly it converges on good behaviour. It appears throughout reinforcement learning, bandit problems and adaptive control. Memory, methodology and evaluation cost are separate trades. A dilemma that arises purely from acting under uncertainty is one of the most general ideas in the subject.

Discuss in Forum

Loading…

Topics

Other Subjects

Tags: Introduction to Artificial Intelligence Questions and Answers || Introduction to Artificial Intelligence MCQ Questions and Answers || Introduction to Artificial Intelligence GK Questions and Answers || Introduction to Artificial Intelligence GK MCQ Questions || Introduction to Artificial Intelligence Multiple Choice Questions and Answers || Introduction to Artificial Intelligence GK || GK on Introduction to Artificial Intelligence || Artificial Intelligence Questions and Answers || Artificial Intelligence MCQ Questions and Answers || Artificial Intelligence GK Questions and Answers || GK on Artificial Intelligence

Introduction to Artificial Intelligence Questions and Answers

Topics

Other Subjects

About Us

Stay informed about all important Dates & Notifications