added types.en.mdx

pages/agents/_meta.en.json

@@ -1,4 +1,5 @@
 {
     "introduction": "Introduction to Agents",
-    "components": "Agent Components"
+    "components": "Agent Components",
+    "types": "Agent Types"
 }

pages/agents/types.en.mdx

@@ -0,0 +1,43 @@
+# **Types of AI Agents**
+
+AI agents are autonomous systems designed to perform tasks, make decisions, and interact with their environment or other agents. In the world of AI, there are various types of agents, each suited for different applications and problem-solving scenarios. Understanding these agent types is essential for designing and engineering efficient AI systems. This page outlines the key types of AI agents, their functionalities, and where they are commonly applied.
+
+### **Simple Reflex Agents**
+
+Simple reflex agents operate on the principle of condition-action rules, where the agent responds to specific stimuli based on predefined rules. They do not remember past actions or states; they react to the current environment only.
+A thermostat that turns on the heater when the temperature drops below a certain threshold is an example of a simple reflex agent.
+
+
+### **Model-Based Reflex Agents**
+
+Model-based reflex agents are an enhancement over simple reflex agents. They maintain an internal model or state of the world, allowing them to make decisions based on both the current and past states of the environment.
+A vacuum cleaner that remembers which areas of the house have already been cleaned and avoids repeating actions in already-cleaned areas is a model-based reflex agent.
+
+
+### **Goal-Based Agents**
+
+Goal-based agents act with the specific objective of achieving a particular goal. They make decisions by considering various possible actions and selecting the ones that will bring them closer to achieving the goal. These agents use planning and reasoning techniques to select the best course of action.
+A self-driving car navigating to a destination by evaluating different routes to avoid traffic is a goal-based agent.
+
+### **Utility-Based Agents**
+
+Utility-based agents evaluate actions based on the utility or expected benefit they will bring. Instead of simply achieving a goal, they aim to maximize performance by selecting actions that provide the highest utility or reward based on the current context.
+An AI trading bot that evaluates different stock market trades based on the expected return or risk to maximize profit is a utility-based agent.
+
+
+### **Learning Agents**
+
+Learning agents improve their performance over time by learning from their experiences and interactions with the environment. These agents adjust their decision-making strategies based on past outcomes to optimize future actions.
+A recommendation system that learns user preferences over time and improves its suggestions based on past interactions is a learning agent.
+
+
+### **Multi-Agent Systems (MAS)**
+
+Multi-agent systems involve multiple agents interacting and collaborating to achieve individual or shared goals. These agents can communicate, negotiate, and coordinate with each other, often working in parallel to solve complex tasks.
+A fleet of delivery drones that cooperatively deliver packages while avoiding collisions and optimizing routes is an example of a multi-agent system.
+
+
+## References
+
+- [Classifications of intelligence agents and their applications](https://journals.tu-plovdiv.bg/index.php/journal/article/view/559) (May 2023)
+