Lecture 2 Flashcards
What is an agent?
Anything that is sceen to perceive its environment through sensors and act upon that environment through actuators.
What is a percept?
The content an agent’s sensors are perceiving.
What is a percept sequence?
The complete history of everything the agent has ever perceived.
What is an agent function?
The agent’s behaviour, which is decribed by mapping any given percept sequence to an action.
What are the four basic kinds of agent functions?
- Simple reflex Agents
- Model-based reflex agents
- Goal-based agents
- Utility-based agents
What is a Simple Reflex Agent?
Selects actions on the basis of the CURRENT percept, ignoring the rest of the percept history. Uses a condition-action rule.
What is a Learning Agent?
Can be built from any type of agent program. Consists of the following components:
1. learning element
2. performance element
3. critic
4. problem generator
Which factors are used to specify an agent’s task environment?
Performance, Environment, Actuators, and Sensors.
List the (7) properties of a task environment
- Fully observable vs Partially observable (or unobservable)
- Single-agent vs Multiagent
- Deterministic vs Non-deterministic
- Episodic vs Sequential
- Static vs Dynamic
- Discrete vs Continous
- Known vs Unknown
What is a Model-based Reflex Agent?
Keeps track of the part of the world it can’t see now. The most effective way to handle partial observability.
What is a Goal-based Agent?
An agent that uses both knowledge of the current environment and information of its goal to decide which situations are desirable.
What is a Utility-based Agent?
Uses a utility function as an internalized performance measure to compare different world states, which allow the agent to see the tradeoff and utility of each state to make take an appropriate action.
