Skip to content

JA2. Learning Journal 2

Your learning journal entry must be a reflective statement that considers the following questions:

Answer

1. Describe what you did. This does not mean that you copy and paste from what you have posted or the assignments you have prepared. You need to describe what you did and how you did it

This was the second week of the course, and we started talking about agents and environments. I started by reading the material provided by the learning guide and then started working on the discussion assignment. I answered the questions about the PEAS framework for different agents, and then did the programming assignment where I had to design a vacuum cleaner agent that cleans a room.

2. Describe your reactions to what you did

I found the discussion assignment to be very interesting. I liked how we had to think about the design of different agents; although it was a long assignment, having to think about agents that work as vacuum cleaners, speech recognition devices, drones, chess players, and personal assistants made the challenge fun.

The programming assignment was also fun, but it was super hard as I spend more than 10 hours on it. Despite the time spent, I enjoyed it as I was using PyGame for the first time, and it felt like game development rather an AI assignment.

3. Describe any feedback you received or any specific interactions you had while participating discussion forum or the assignment Discuss how they were helpful

I was surprised that my classmates were able to provide answers for the discussion assignment with less words; my assignment was very long compared to theirs. I received feedback that I need to make it shorter but I was not able to omit any of the information I wrote, as I thought it was necessary to explain my answers. I introduced my answer with a detailed explanation of the PEAS framework and then answered the questions for each agent, detailing the process of determining each component of the environment. I need to work on making my answers more concise.

4. Describe your feelings and attitudes

I felt very happy and satisfied after finishing the programming assignment despite the long time spent on it. I was unhappy though with the level of my classmates’ participation in the discussion forum; I found many submissions to be very shallow and missing the point.

5. Describe what you learned. You can think of one or more topics and explain your understanding in writings. Feel free to add any diagram or coding example if that helps you explain better

The week started talking about agent design and how an agent sets in an environment and interacts with it through its sensors and actuators. The sensors read the environment and deliver its information as a precept to the agent’s controller (brain), which then decides what to do and sends a command to the actuators to perform an action.

The types of environments includes fully vs partially observable, single-agent vs multi-agent, deterministic vs stochastic, discrete vs continuous, known vs unknown, and static vs dynamic. The PEAS framework is a useful tool to understand the design of agents, and it divides the agent’s design into 4 components: Performance, Environment, Actuators, and Sensors.

Hierarchical control is a way to design agents that have multiple layers of control, where each layer is responsible for a different aspect of the agent’s behavior. The information reaches the lower layers first, where they decide if they want to respond or pass the information to the higher layers. This way keeps the agent’s design modular and easy to maintain.

6. Did you face any challenges while doing the discussion or the development assignment? Were you able to solve it by yourself?

The programming assignment was particularly challenging for me. Not the working code itself, but rather me trying to design my code in a way similar to what we have learned in this week. That is, I tried to keep my code as modular as possible while having different layers and hierarchies calling each other, but that was difficult.

I overcome this challenge by recording everything in the environment into one central state and ended up passing this state around to all different functions in my code. This is may not be the best way, nor it is the way recommended in the assignment, but I reached it after multiple trials and errors.

Here is the shape of central state I used, you see that it includes information about the internals of the vacuum, the external environment, and some abstract information about the goal:

    state = {
        "vacuum_pos": {"x": 0, "y": 0},
        "cols": 4,
        "rows": 4,
        "dirtyTiles": [{"name": "D", "x": 1, "y": 1}],
        "history": [],
        "current_command": None,
        "energy": 100,
        "energy_capacity": 100,
        "bag": 0,
        "bag_capacity": 10,
        "target_pos": {"x": 0, "y": 0},
        "goal_achieved": False
    }

References