Artificial Intelligence
History and Application
Types of AI
Agents in AI
Types of AI Agents
Agent Environment
Turing Test in AI
Search Algorithms
Uninformed Search Algorithms
Informed Search Algorithms
Hill Climbing Algorithm
Means Ends Analysis
Adversarial Search
Mini-Max Algorithm
Alpha-Beta Pruning
Knowledge-based Agent
Knowledge Representation
Knowledge Representation Techniques
Propositional Logic
Rules of Inference
The Wumpus World
Knowledge Base for Wumpus World
First Order Logic
Knowledge Engineering in FOL
Inference in FOL
Unification in FOL
Resolution in FOL
Forward and Backward Chaining
Reasoning in AI
Bayesian Belief Network
Types of Artificial Intelligence (AI) Agents
In this page we will learn What are the types Artificial Intelligence (AI) agents?, Simple Reflex agent, Model-based reflex agent, Goal-based agents, Utility-based agents, Learning Agents.
What are the types Artificial Intelligence (AI) agents?
Based on their apparent intelligence and capability, agents are divided into five categories. Over time, any of these agents can increase their performance and generate better action. The following are some of them:
- Simple Reflex Agent
- Model-based reflex agent
- Goal-based agents
- Utility-based agent
- Learning agent
1. Simple Reflex agent:
- The simplest agents are simple reflex agents. These agents make decisions based on their current perceptions while disregarding the remainder of their perception history.
- Only in a fully visible environment these agents can succeed.
- During the decision and action process, the Simple reflex agent does not consider any aspect of the percepts history.
- Simple reflex agent work on the Condition-action rule, which implies it maps the current state to an action. A Room Cleaner agent, for example, only works if there is dust in the room.
- Problems with the simple reflex agent design technique include the following:
-
- Their IQ is severely limited.
- They are unaware of non-perceptual aspects of the current situation.
- The majority of them are too large to generate and store.
2. Model-based reflex agent
- The model-based agent can track the situation in a partially observable environment.
- There are two crucial components in a model-based agent:
-
- Model: A Model-based agent is one that has information about "how things happen in the world."
- Internal State: It is a perceptually based representation of the current state.
- These agents have a model, "which is knowledge of the world," and they behave in accordance with it.
- Updating the agent state necessitates knowledge of:
-
- The Way the World Changes.
- The impact of the agent's actions on the rest of the world.
3. Goal-based agents
- Knowing the current status of the environment isn't always enough to help an agent decide what to do.
- By having the "target" information, goal-based agents extend the capabilities of model-based agents.
- They decide on a course of action in order to achieve their aim.
- Before deciding whether or not the goal has been met, these agents may have to analyze a vast list of possible actions. Such analyses of many scenarios are referred to as searching and planning, and they enable an agent to be proactive.
4. Utility-based agents
- These agents are comparable to goal-based agents, but they have a utility measurement component that distinguishes them by providing a measure of success at a given state.
- Utility-based agents act in accordance with not only their goals, but also the most efficient means of achieving them.
- The utility-based agent comes in handy when there are several options to pick from and an agent must determine the optimum action.
- The utility function converts each state into a real value, allowing you to see how well each action accomplishes the objectives.
5. Learning Agents
- It begins by acting with minimal information and subsequently learns to act and adapt automatically.
- The following are the four fundamental conceptual components of a learning agent:
-
- Learning Element: It is in charge of improving the environment by learning from it.
- Critic: The learning element receives input from the critic, which specifies how well the agent is performing in comparison to a predetermined benchmark.
- Performance Element: It is in charge of selecting external action as a performance element.
- Problem generator: This component is in charge of recommending behaviors that will lead to novel and educational experiences.