Adaptive AI Engine for RTS Games

Discussing the theory and practice

Archive for the ‘Platforms’ Category

CaS System – An Introduction

Posted by Ogail on December 14, 2009

Hello all,

I’d like to introduce CaS (Case-Based Strategies) its a CBR system that is able to adapt itself depending of the opponent strategies. We consider CaS as a future work for CaT (CBR system developed bt David W. Aha). CaS is a mixture of CBR techniques and is mapped to BDI model. Till now we’ve finished the design of:

  • Case representation technique.
  • Retrieval method.
Advertisements

Posted in CaS-RTS Platform | Leave a Comment »

Case Based Planner Platform For RTS Games

Posted by Ogail on December 6, 2009

Posted in CaS-RTS Platform, Presentations | Tagged: , , , , , , , | Leave a Comment »

Introduction To Heuristically accelerated Hierarchical RL in RTS Games

Posted by merothehero on December 5, 2009

Posted in HAHRL-RTS Platform | Tagged: , , , | 1 Comment »

Just an Intro : Heuristically Accelerated Hierarchical Reinforcement Learning in RTS Games

Posted by merothehero on December 3, 2009

Introduction

In this document I will analyze the game play and strategies of RTS Games, and then I will give a brief about how the Heuristically Accelerated Hierarchical Reinforcement Learning System (HAHRL-RTS System) will work.

The Strategy Game: An Analysis

There’s no doubt that strategy games are complex domains: Gigantic set of allowed Actions (almost infinite), Gigantic set of Game States (almost infinite), imperfect information, nondeterministic behavior, and with all this: Real-time Planning and Reactions are required.

Many of the Approaches to applying learning or planning to RTS Games considered the AI as one solid learning part; this leads to the great complexity at applying the techniques used.

I thought about: How can I simplify everything?

Firstly, I listed all the primitive actions which could be done by a human player:

1-      Move a unit

2-      Train/Upgrade a unit

3-      Gather a resource

4-      Make a unit attack

5-      Make a unit defend

6-      Build a building

7-      Repair a building

NB: Upgrading units or buildings is not available in BosWars but found in most RTS Games.

Any player wins by doing 2 types of actions simultaneously, either an action that strengthens him or an action that weakens his enemy (Fig 1).
NB: We neglect useless actions here and suppose the player is perfect.

When a human plays a strategy game, he doesn’t learn everything at the same time. He learns each of the following 6 sub-strategies separately:

1-      Train/Build/Upgrade attacking Units: What unit does he need to train??

  1. Will he depend on fast cheep units to perform successive fast attacks or powerful expensive slow units to perform one or two brutal attacks to finish his enemy? Or will it be a combination of the two which is often a better choice?
  2. Does his enemy have some weak points concerning a certain unit? Or his enemy has units which can infiltrate his defenses so he must train their anti-units?
  3. Does he prefer to spend his money on expensive upgrades or spend it on more amounts of non-upgraded units?

NB: I deal with attacking Buildings as static attacking units

2- Defend: How will he use his current units to defend?

  1. Will he concentrate all his units in one force stuck to each other or will he stretch his units upon his borders? Or a mix of the two approaches?
  2. Will he keep the defending units (which maybe an attacking building) around his buildings or will he make them guard far from the base to stop the enemy early. Or a mix of the two approaches?
  3. If he detects an attack on his radar, will he order the units to attack them at once, or will he wait for the opponent to come to his base and be crushed? Or a mix of the two approaches?
  4. How will he defend un-armed units? Will he place armed units near them to for protection or will he prefer to use the armed units in another useful thing? If an un-armed unit is under attack how will he react?
  5. What are his reactions to different events while defending?

3- Attack: How will he use his current units to attack?

  1. Will he attack the important buildings first? Or will he prefer to crush all the defensive buildings and units first? Or a mix of the two approaches?
  2. Will he divide his attacking force to separate small forces to attack from different places, or will he attack with one big solid force? Or a mix of the two approaches?
  3. What are his reactions to different events while attacking?

4- Gather Resources: How will he gather the resources?

  1. Will he train a lot of gatherers to have a large rate of gathering resources? Or will he train a limited amount because it would be a waste of money and he wants to rush (attack early) in the beginning of the game so he needs that money? Or a mix of the two approaches?
  2. Will he start gathering the far resources first because the near resources are more guaranteed? Or will he be greedy and acquire the resources the nearer the first? Or a mix of the two approaches?

5-      Construct Buildings: How does he place his buildings? Will he stick them to each other in order to defend them easily? Or will he leave large spaces between them to make it harder for the opponent to destroy them? Or a mix of the two approaches?

6-      Repair: How will he do the repairing? Although it’s a minor thing, but different approaches are used. Will he place a repairing unit near every building in case of having an attack, or will he just order the nearest one to repair the building being attacked? Or a mix of the two approaches?

The HAHRL-RTS System

Since the 6 sub-strategies do not depend on each other (think of it and you’ll find them nearly independent),  So, I will divide the AI system to a hierarchy as shown in figure 1, each child node is by itself a Semi-Marcov decision process (SMDP) where Heuristically Accelerated Reinforcement Learning Techniques will be applied. Each child node will be later divided into other sub-nodes of SMDPs.

So now you’ve understood why it is hierarchical, but you may be wondering why “heuristically accelerated”?

Well, because heuristic algorithms will be applied to guide and accelerate the learning process. I hear you asking what the heuristic algorithms are. But that’s another story will be said later!

Posted in HAHRL-RTS Platform | Tagged: , , , , | Leave a Comment »

Cases Representation Techniques

Posted by Ogail on December 2, 2009

  1. Hash Map.

The key (identifier) of each element will be determined using a hash function depends on the identifier features of the case.

  1. A Simplex Plan.

The problem of acquiring amount of peons to train will be formalized in a Simplex method form and then solved.

  1. Hierarchical Memory Structure.

The most important features are placed in the top of this hierarchy and the less important ones led us to certain sub groups of cases till we reach the most similar cases to the new one we have.

Posted in CaS-RTS Platform | Leave a Comment »

Case Retrieval Technique

Posted by Ogail on December 1, 2009

  • Abstract:
    • Any case-based planning system deals with 5 problems: Case representation, retrieval, reuses, revise and retain. In this article we discuss the case retrieval of the CBP system.
  • In this article we are only restricted with example of collecting a resource for a certain amount.
  • We have three alternative techniques of retrieving cases:
    • Simplex algorithm:
      • The whole cases are just represented in one case.
      • Using Simplex method algorithm you can calculate number of peons required to collect the resource.
    • Hashing:
      • The cases will be retained in a map data structure and its index will be calculated from equation:
      • I = aX + bY + cZ
      • Where:
        • I: is the key of case in the map.
        • X: is number of gold mines in the map.
        • Y: is the number of free or useless peon.
        • Z: amount of gold required.
        • a, b, c are weights for the features.
    • Hierarchal Structure:
      • The cases will be represented as a hierarchy.
      • The most important features are placed in the top of this hierarchy and the less important ones led us to certain sub groups of cases till we reach the most similar cases to the new one we have.

Posted in CaS-RTS Platform | Leave a Comment »

Case Representation Technique

Posted by Ogail on December 1, 2009

  • Abstract:
    • Any case-based planning system deals with 5 problems: Case representation, retrieval, reuses, revise and retain. In this article we discuss the case representation (the plan contents and the case base design) of the CBP system.
  • We define a case C as a tuple of four objects:
    • C = <Goal(s), WorldState, Plan, Performance>
    • Where:
      • Goal(s): goal(s) that this case satisfies.
      • WorldState: is the state of the world in the current situation.
      • Plan: sequence of actions that will achieve the goal(s).
      • Performance: is a real value in the range [0,1] that reflects the utility of choosing that case for that state, where higher values indicate higher performance.
  • We’ve found that it’s wasting of memory and time if we make all of the cases contain the same WorldState because certain cases just require a little knowledge of the world to work. As an example suppose that we need to represent a case for solving problem of collecting a resource with a certain amount, what would the number of assaults I have will help in this problem? Rather we just need a little knowledge that will help. Below the case representation of the resource collecting goal:
    • Goal:
      • CollectResource (Gold, MaxInfluence).
    • WorldState:
      • Number of gold mines.
      • Distance between gold mines and nearest gold mine collector.
      • Number of free or useless peons.
    • Plan:
      • Train(3, peon).
      • Assign(3, peons, GoldMiner).
      • Build(1, Farm).
    • Performance:
  • Number of gold collected in 1 minute.

Posted in CaS-RTS Platform | Leave a Comment »