Creating the mini game and facing the ML-Agent

Based on our last project, we are going to use all that we are learned to create a Mini Game where the NPC will be managed by ML-Agents.

This project works without a conda environment, since we will use a previously created file containing the result of a learning process.

Ml-Agents script:

using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using UnityEngine.UI;
using Unity.MLAgents;
using Unity.MLAgents.Sensors;
public class HumanoidML : Agent
{
    [Header("Velocidad")]
    [Range(0f, 5f)]
    public float _speed;
    [Header("Velocidad de giro")]
    [Range(50f, 300f)]
    public float _turnSpeed;
    public bool _training = true;
    private Rigidbody _rb;
    [SerializeField]
    private Transform _target;
    private Animator _anim;
    private Vector3 _previous;
    public Text _contadorText = null;
    public float _puntos = 0; 
    public override void Initialize()
    {
        _rb = GetComponent<Rigidbody>();
        _anim = GetComponent<Animator>();
        _previous = transform.position;
        //MaxStep forma parte de la clase Agent
        if (!_training) MaxStep = 0;
    }
    public override void OnEpisodeBegin()
    {
        _rb.velocity = Vector3.zero;
        _rb.angularVelocity = Vector3.zero;
        MoverPosicionInicial();
        _previous = transform.position;
    }
    public override void OnActionReceived(float[] vectorAction)
    {
        float lForward = vectorAction[0];
        float lTurn = 0;
        if (vectorAction[1] == 1)
        {
            lTurn = -1;
        }
        else if (vectorAction[1] == 2)
        {
            lTurn = 1;
        }
        _rb.MovePosition(transform.position +
            transform.forward * lForward * _speed * Time.deltaTime);
        transform.Rotate(transform.up * lTurn * _turnSpeed * Time.deltaTime);
    }
    public void Update()
    {
        float velocity = ((transform.position - _previous).magnitude) / Time.deltaTime;
        _previous = transform.position;
        _anim.SetFloat("multiplicador", velocity);
    }
    public override void Heuristic(float[] actionsOut)
    {
        float lForward = 0f;
        float lTurn = 0f;
        if (Input.GetKey(KeyCode.UpArrow))
        {
            lForward = 1f;
        }
        if (Input.GetKey(KeyCode.LeftArrow))
        {
            lTurn = 1f;
        }
        else if (Input.GetKey(KeyCode.RightArrow))
        {
            lTurn = 2f;
        }
        // Put the actions into an array and return
        actionsOut[0] = lForward;
        actionsOut[1] = lTurn;
    }
    public override void CollectObservations(VectorSensor sensor)
    {
        //Distance to the target.
        sensor.AddObservation(
        Vector3.Distance(_target.transform.position, transform.position));
        //Direction to the target.
        sensor.AddObservation(
            (_target.transform.position - transform.position).normalized);
        //Character's Forward vector.
        //Vector de 3 posiciones. 
        sensor.AddObservation(
            transform.forward);
    }
    private void OnTriggerStay(Collider other)
    {
        if (true)
        {
            if (other.CompareTag("target"))
            {
                DaPremio(0.5f);
            }
            if (other.CompareTag("borders"))
            {
                DaPremio(-0.05f);
            }
        }
    }
    private void DaPremio(float premio)
    {
        AddReward(premio);
        if (_contadorText != null)
        {
            _puntos += premio;
            _contadorText.text = _puntos.ToString();
        }
    }
    private void MoverPosicionInicial()
    {
        bool posicionEncontrada = false;
        int intentos = 100;
        Vector3 posicionPotencial = Vector3.zero;
        while (!posicionEncontrada || intentos >= 0)
        {
            intentos--;
            posicionPotencial = new Vector3(
                transform.parent.position.x + UnityEngine.Random.Range(-3f, 3f),
                0.555f,
                transform.parent.position.z + UnityEngine.Random.Range(-3f, 3f));

            Collider[] colliders = Physics.OverlapSphere(posicionPotencial, 0.5f);
            if (colliders.Length == 0)
            {
                transform.position = posicionPotencial;
                posicionEncontrada = true;
            }
        }
    }
}

As you can see we have a lot of possibilities when we talk about NPC creation. We can use different configurations files to create ml-agents with different behaviours. Some more trained, some less trained. Or some trained to reach the same target, but in a different way.

We have seen just the most basic of ml-agents, but in a short time and now we have a solid knowledge base to start exploring the world of Artificial Intelligence using Machine Learning in UNITY to improve our games.