Agents in AI
The study of logical agents is referred to as artificial intelligence. Anything that makes decisions, whether it be a person, business, computer, or piece of software, is a rational agent. After taking into account both previous and present percepts (the agent’s perceptual inputs at a given instance), it performs an action with the best result. An agent and its surroundings make up an AI system. In their surroundings, the agents behave. Other agents could be present in the environment.
Anything that can be considered an agent is using sensors to perceive its environment and actuators to make changes to it.
Types of Agents
Model-based reflex agents
It operates by identifying a rule whose condition corresponds to the current circumstance. By using a model of the world, a model-based agent may manage partially observable environments. The agent must monitor its internal state, which is altered by each perception and is influenced by its prior perceptions. The agent stores the current state and keeps some sort of structure describing the invisible portion of the universe.
When updating the state, we need to know how the world changes without the agent and how the agent’s activities have an impact on the world.
Goal-based agents
These types of agents make choices dependent on how far they are from their objective at the moment (description of desirable situations). Every action they take aims to bring them closer to their objective. This gives the agent the ability to select from a variety of options, choosing the one that leads to the goal state. These agents are more adaptable because the knowledge that underpins their decisions is expressed directly and is modifiable. Typically, they call for research and preparation. The behaviour of the goal-based agent is easily modifiable.
Utility-based agents
These kinds of agents make decisions based on how distant they are now from their goal (description of desirable situations). Every move they perform is intended to advance them toward their goal. This enables the agent to choose from a variety of possibilities and take the path that leads to the desired state. Because the knowledge that guides these agents’ decisions is directly articulated and adjustable, it makes them more adaptive. They typically require planning and study. The goal-based agent’s behaviour can be simply changed.
Learning Agent
An AI agent with learning capabilities or the ability to learn from its experiences in the past is referred to as a “learning agent.” Beginning with basic information, it may then act and adapt on its own through learning.
A learning agent primarily consists of these four conceptual parts:
Element of learning: It is accountable for producing advancements by absorbing environmental knowledge.
Critic: The learning component uses criticism to gauge how well the agent is performing in relation to a predetermined performance benchmark.
Element of performance: It is in charge of choosing an external action.
Problem Generator: This element is in charge of making recommendations for actions that will result in novel and educational experiences.
