From 82219b9882776a79f55793c8bf5f5cd1638cd828 Mon Sep 17 00:00:00 2001
From: Ariel Kwiatkowski <ariel.j.kwiatkowski@gmail.com>
Date: Fri, 26 May 2023 14:44:28 +0100
Subject: [PATCH] Clamp the avg energy heuristic

---
 Assets/Scenes/NormalScene.unity | 4 +++-
 Assets/Scripts/MLUtils.cs       | 3 +++
 Assets/Scripts/Params.cs        | 3 +++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/Assets/Scenes/NormalScene.unity b/Assets/Scenes/NormalScene.unity
index 7b42c4f..9dfa465 100644
--- a/Assets/Scenes/NormalScene.unity
+++ b/Assets/Scenes/NormalScene.unity
@@ -600,7 +600,7 @@ MonoBehaviour:
   spawnScale: 7
   gridSpawn: 1
   groupSpawnScale: 1.5
-  enableObstacles: 1
+  enableObstacles: 0
   blockScale: 3
   randomMass: 1
   randomEnergy: 0
@@ -621,6 +621,7 @@ MonoBehaviour:
   rewardVelocityMatching: 1
   rewardGoal: 1
   rewardFinal: 1
+  rewardAvgFinal: 1
   sightRadius: 10
   sightAgents: 12
   sightAngle: 180
@@ -6263,6 +6264,7 @@ MonoBehaviour:
   PreferredSpeed: 1.33
   mass: 1
   squasherType: 3
+  startPosition: {x: 0, y: 0, z: 0}
   CollectedGoal: 0
   rewardDisabled: 0
   distanceTraversed: 0
diff --git a/Assets/Scripts/MLUtils.cs b/Assets/Scripts/MLUtils.cs
index c212c0d..1984a92 100644
--- a/Assets/Scripts/MLUtils.cs
+++ b/Assets/Scripts/MLUtils.cs
@@ -2,6 +2,7 @@
 using System.Collections.Generic;
 using System.Diagnostics.Contracts;
 using System.Linq;
+using System.Reflection;
 using Managers;
 using UnityEngine;
 using Random = UnityEngine.Random;
@@ -259,6 +260,8 @@ public static float AverageEnergyHeuristic(Vector3 position, Vector3 target, Vec
         
         
         var avgSpeed = (totalDistance - finalDistance) / timeLimit;  // v'
+
+        avgSpeed = Mathf.Max(avgSpeed, Params.HeuristicEpsilon);
         
         var remainingTime = finalDistance / avgSpeed;  // T'
         
diff --git a/Assets/Scripts/Params.cs b/Assets/Scripts/Params.cs
index 532becd..3e86aa0 100644
--- a/Assets/Scripts/Params.cs
+++ b/Assets/Scripts/Params.cs
@@ -135,6 +135,9 @@ private void Awake()
     public float rewardAvgFinal = 1f;
     public static float RewAvgFinal => Get("r_avg_final", Instance.rewardAvgFinal);
     
+    public float heuristicEpsilon = 0.1f;
+    public static float HeuristicEpsilon => Get("heuristic_epsilon", Instance.heuristicEpsilon);
+