ml-agents/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentCollab.cs

//Put this script on your blue cube.

using System.Collections;
using UnityEngine;
using Unity.MLAgents;
using Unity.MLAgents.Actuators;
using Unity.MLAgents.Sensors;

public class PushAgentCollab : Agent
{

    PushBlockSettings m_PushBlockSettings;

    //    Rigidbody m_BlockRb;  //cached on initialization
    Rigidbody m_AgentRb;  //cached on initialization

    public bool useVectorObs = true;
    void Awake()
    {
        m_PushBlockSettings = FindObjectOfType<PushBlockSettings>();
    }

    public override void Initialize()
    {
        // Cache the agent rigidbody
        m_AgentRb = GetComponent<Rigidbody>();
    }

    /// <summary>
    /// Moves the agent according to the selected action.
    /// </summary>
    public void MoveAgent(ActionSegment<int> act)
    {
        var dirToGo = Vector3.zero;
        var rotateDir = Vector3.zero;


        var forwardAxis = act[0];
        var rightAxis = act[1];
        var rotateAxis = act[2];

        switch (forwardAxis)
        {
            case 1:
                dirToGo = transform.forward * 1f;
                break;
            case 2:
                dirToGo = transform.forward * -1f;
                break;
        }

        switch (rightAxis)
        {
            case 1:
                dirToGo = transform.right * 1f;
                break;
            case 2:
                dirToGo = transform.right * -1f;
                break;
        }

        switch (rotateAxis)
        {
            case 1:
                rotateDir = transform.up * -1f;
                break;
            case 2:
                rotateDir = transform.up * 1f;
                break;
        }

        transform.Rotate(rotateDir, Time.fixedDeltaTime * 200f);
        m_AgentRb.AddForce(dirToGo * m_PushBlockSettings.agentRunSpeed,
            ForceMode.VelocityChange);
    }

    public override void CollectObservations(VectorSensor sensor)
    {
        if (useVectorObs)
        {
            sensor.AddObservation(StepCount / (float)MaxStep);
        }
    }

    /// <summary>
    /// Called every step of the engine. Here the agent takes an action.
    /// </summary>
    public override void OnActionReceived(ActionBuffers actionBuffers)

    {
        // Move the agent using the action.
        MoveAgent(actionBuffers.DiscreteActions);

        // Penalty given each step to encourage agent to finish task quickly.
        //AddReward(-1f / MaxStep);
    }

    public override void Heuristic(in ActionBuffers actionsOut)
    {
        var discreteActionsOut = actionsOut.DiscreteActions;
        discreteActionsOut.Clear();
        //forward
        if (Input.GetKey(KeyCode.W))
        {
            discreteActionsOut[0] = 1;
        }
        if (Input.GetKey(KeyCode.S))
        {
            discreteActionsOut[0] = 2;
        }
        //rotate
        if (Input.GetKey(KeyCode.A))
        {
            discreteActionsOut[2] = 1;
        }
        if (Input.GetKey(KeyCode.D))
        {
            discreteActionsOut[2] = 2;
        }
        //right
        if (Input.GetKey(KeyCode.E))
        {
            discreteActionsOut[1] = 1;
        }
        if (Input.GetKey(KeyCode.Q))
        {
            discreteActionsOut[1] = 2;
        }
    }

    /// <summary>
    /// In the editor, if "Reset On Done" is checked then AgentReset() will be
    /// called automatically anytime we mark done = true in an agent script.
    /// </summary>
    public override void OnEpisodeBegin()
    {
    }

}