AutonomousAgents Flashcards

1
Q

What is the literal meaning of “agent” from Latin?

A

Those who act

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the fundamental role of an agent?

A

Someone who acts on behalf of others with power derived from delegation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Name four real-world examples of agents

A

Secret Agents; Travel Agents; Sports/Showbiz Agents; Purchasing Agents

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are the four common characteristics of real-world agent jobs?

A

They engage in specific goal tasks; Are delegated by someone; Have power and knowledge to act; Can decide actions based on conditions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What defines a software agent’s goal?

A

Achieving or maintaining a specific situation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Name two examples of filtering software agents

A

Antivirus and anti-spam agents

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are the four key characteristics of software agents?

A

Goal-oriented; Autonomous; Situated; Social

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How does a software agent differ from a typical process in goal handling?

A

A software agent is designed to achieve goals and can change behavior while a process simply executes predefined algorithmic code

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What makes modern processes similar to agents?

A

They adapt to serve best; Capable of unsolicited execution; Adaptive; Situated; Social

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What does it mean for an agent to be “situated”?

A

It executes in a specific environment and can sense and affect that environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What does “social” mean in the context of software agents?

A

Interacts with other agents in a multiagent system

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is meant by “goal-orientedness” in agents?

A

Agents don’t execute algorithms but aim to achieve a specific state of affairs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How does agent autonomy differ from traditional software control?

A

Agents use distributed decision-making with sub-goals rather than centralized control

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What aspects define agent sociality?

A

Exchange of knowledge; Delegation of tasks; Assignment of roles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What are three key differences between processes and agents?

A

Function-oriented vs Goal-oriented; Centralized vs Decentralized decision-making; Simple vs Sophisticated interactions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What makes self-driving cars exemplary autonomous agents?

A

They have goals navigation goals; Have knowledge of rules; Can sense conditions; Act on controls; Must minimize danger; Decide actions dynamically

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are “beliefs” in agent knowledge?

A

Knowledge about the current state of affairs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What are “desires” in agent knowledge?

A

Knowledge about the desired state of affairs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What are “effects” in agent knowledge?

A

Knowledge of how actions can change the current state of affairs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is theoretical reasoning in agents?

A

A process which affects beliefs to increase knowledge about what’s happening

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What is practical reasoning in agents?

A

Weighing conflicting considerations based on desires and beliefs to choose actions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What are the two components of practical reasoning?

A

Deliberation (deciding to act) and Means-End Reasoning (deciding how to act)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the main challenge of using deep learning in agents regarding XAI?

A

Deep learning makes agents “black boxes” making it difficult to explain their decisions

24
Q

What is the key contrast between deep learning and traditional agents?

A

Deep Learning: Black-box not explainable not symbolic; Agents: White-box explainable symbolic

25
Q

What are the six main types of agent architectures?

A

Reactive; Reactive with State; Proactive goal-oriented; Proactive utility-oriented; Hybrid proactive; Reinforcement Learning

26
Q

What defines a reactive agent?

A

Perceives events and acts based on simple rules with implicit goals

27
Q

What are the advantages and disadvantages of reactive agents?

A

Advantages: Simple and efficient; Disadvantages: Not flexible and not truly autonomous

28
Q

Give three examples of reactive agents

A

Temperature agent; Simple mail agent; Roomba robot

29
Q

How does a reactive agent with state differ from a simple reactive agent?

A

Maintains internal knowledge and can make decisions based on both current perception and past state

30
Q

What are two examples of reactive agents with state?

A

Mail agent that tracks user markings; Roomba robot that maps environment

31
Q

What defines a proactive goal-oriented agent?

A

Has explicit knowledge of goals and selects actions to approach the goal

32
Q

What are the two types of planning in goal-oriented agents?

A

Offline planning (predefined plans) and Online planning (using planning algorithm)

33
Q

What is a causal model in agent planning?

A

Specifies the effect of actions on the environment probabilistically

34
Q

What are the two types of planning algorithms?

A

Greedy planning (single action at a time) and Multistep planning (sequences of actions)

35
Q

What defines a utility-oriented agent?

A

Aims to maximize a specific current utility or preserve quality of specific conditions

36
Q

What is the key difference between goal-oriented and utility-oriented agents?

A

Goal-oriented evaluate current vs desired state; Utility-oriented evaluate a utility function against desired value

37
Q

What is a hybrid architecture in agents?

A

Mixes utility and goals requiring trade-offs between the two

38
Q

What is Newell’s Principle of Rationality?

A

The rational choice is the one that given current knowledge is most suitable to accomplish/approach the goal

39
Q

What are the two main limitations of the rationality principle?

A

Knowledge can be partial/incorrect; World can dynamically change as agent acts

40
Q

What defines reinforcement learning in agents?

A

Self-supervised learning where agent learns how to act through rewards

41
Q

What are the key components of reinforcement learning?

A

Set of actions; Policy for selecting actions; Observation of environment; Reward measurement

42
Q

What is model-based reinforcement learning?

A

Focuses on learning explicit representation of relationship between environment state and agent actions

43
Q

What is the main advantage of model-based RL?

A

Builds a reusable inspectable and explainable model of the world

44
Q

What is model-free reinforcement learning?

A

Doesn’t construct explicit world model relies on exploration to determine rewarding actions

45
Q

What is Q-Learning?

A

Traditional approach to model-free RL that builds a Q-Table matrix associating values to actions in given states

46
Q

What is Deep Q-Learning?

A

Embeds the policy (Q-table) into a Deep Neural Network for handling large state dimensions

47
Q

What are the advantages and disadvantages of Deep Q-Learning?

A

Advantages: Learns complex behaviors handles large spaces; Disadvantages: Lacks explainability not reusable costly learning

48
Q

What is SOTA in agent systems?

A

State of Affairs representing current desired condition within environment

49
Q

What defines a goal in SOTA phase space?

A

Reaching a particular area in the SOTA phase space

50
Q

What are the two conditions that characterize goals?

A

Precondition (when goal should activate) and Postcondition (what achievement implies)

51
Q

What are utilities in SOTA phase space?

A

Constraints on how goals can be reached within the system

52
Q

What is the BDI model?

A

Belief-Desire-Intention model for operational way to think about goal-oriented agents

53
Q

What are the three key components of BDI?

A

Beliefs (knowledge about world); Desires (goals); Intentions (currently activated goals)

54
Q

What is JADE?

A

A goal-oriented agent system where agents have state and behaviors for sub-tasks

55
Q

What is Jason?

A

A declarative language for BDI agent-oriented programming using logic-programming approaches