Game A.I.

  1. Introduzione alla A.I.
  • storia
  • stato dell’arte
  • etica e opportunità
  1. Machine Learning: i fondamentali
  • Neural Networks: le basi e il potenziale
  • GAN (Generative adversarial network) come funzionano?
  1. Metodi AI nei videogiochi
  • Utility
  • FSM / Behavior Trees
  • TreeSearch / Pathfinding
  • Evolutionary Computation / Genetic
  • Supervised Learning
  • Reinforcement Learning
  • Unsupervised Learning
  • Planners
  • Random / Fuzzy / Noise
  1. AI per giocare
  • avversari
  • playtest
  • demo
  1. AI per generare contenuti
  • Livelli e Mappe
  • Visual
  • Audio
  • Narrativa
  1. case studies spettacolari e futuro

NB: Il Repository Pubblico di questo libro è https://github.com/StefanoCecere/book_2042GameDev

  • Introduzione e Metodi

    video The Mind Game Introduzione alla A.I. storia: inizio anni 50, turing giocare a scacchi senza computer modellare l’intelligenza deterministici Deep Blu fine anni ‘90 Narrow/Weak AI & Strong (true) AI / AGI AI e Videogiochi giocare (NPG e player) creare contenuti analizzare gameplay e modellare il giocatore big data & GPU power -> ML AI & Videogames AI Plays and Improves Your Game.

  • GOAP

    Goal-Oriented Action Planner Unity Learn Udemy course Unity Labs Behavioral AI Research UNITY AI PLanner ai.planner docs ai.planner samples ai.planner video

  • Play

    good AI let the player cheat non deve essere troppo prevedibile ma neanche deve essere perfetta lascia il giocatore “vincere” MarI/O – Machine Learning in Video Games https://youtu.be/qv6UVOQ0F44

  • Generate Content

    Procedural Content Generation (PCG) cosa si può generare? – NPC behavior – Quest / story / narrativa – Audiovisual settings – Livelli / Mappe / Percorsi – Items / Weapons – Game mechanics / Rules – Reward schedules

  • L-Systems

    examples to be used in http://www.malsys.cz/Process Koch CUrve lsystem KochCurve { set compressSvg = false; set symbols axiom = F; // F - - F - - F; set iterations = 1; // normalize line length to have (result image will have always same size) interpret F as DrawForward(2 ^ -(currentIteration * 3 / 2) * 512); interpret + as TurnLeft(60); interpret - as TurnLeft(-60); rewrite F to F + F - - F + F; } process all with SvgRenderer; HilbertCurve lsystem HilbertCurve { set compressSvg = false; set symbols axiom = L; set iterations = 2; interpret F as DrawForward(8); interpret + as TurnLeft(90); interpret - as TurnLeft(-90); rewrite L to + R F - L F L - F R +; rewrite R to - L F + R F R + F L -; } process all with SvgRenderer; plant lsystem Plant3 { set symbols axiom = F(0); set initialAngle = 90; set iterations = 1; set randomSeed = 0; set compressSvg = false; interpret F(x) as DrawForward(12, 1+x*2, darken(#00FF00, random(0 + 0.

  • Unity ml-agents

    https://unity3d.com/machine-learning/ https://github.com/Unity-Technologies/ml-agents examples: https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md Unity CNN styles https://blogs.unity3d.com/2020/11/25/real-time-style-transfer-in-unity-using-deep-neural-networks/ the future of ml-agents https://blogs.unity3d.com/2020/12/28/happy-holidays-from-the-unity-ml-agents-team/ Puppo: https://blogs.unity3d.com/2018/10/02/puppo-the-corgi-cuteness-overload-with-the-unity-ml-agents-toolkit/ Designing safer cities through simulations: https://blogs.unity3d.com/2018/01/23/designing-safer-cities-thr

  • Resources

    Unity Courses Artificial Intelligence for Beginners (15 hours) https://learn.unity.com/course/artificial-intelligence-for-beginners The Beginner’s Guide to Artificial Intelligence in Unity. https://www.udemy.com/course/artificial-intelligence-in-unity/ AI Courses https://www.coursera.org/learn/ai-for-everyone PyTorch https://www.devry.edu/online-programs/courses/machine-learning-with-pytorch.html ML https://madewithml.com/ Books Unity Artificial Intelligence Programming - Packt pub.

  • Install ml-agents

    installare ml-agents procedure per installare Python + ml-agents su Windows 64 bit useremo la versione Verified Package 1.0.6. docs ufficiali: https://github.com/Unity-Technologies/ml-agents/blob/release_2_verified_docs/docs/Readme.md metodo 1: diretto (più veloce) scaricare Windows x86-64 executable installer da https://www.

  • Exercises

    Esercizio 1 scegliere un board game (più è semplice meglio è). descrivere il processo mentale del giocatore, con tutti i passaggi logici, come se potesse essere tradotto in AI. FORM: https://forms.

  • PacMan AI AI learns to play PACMAN || Part 1 the making of Pacman https://www.youtube.com/watch?v=qwhXIzNrb9w optional: Pac-Man Ghost AI Explained https://www.youtube.com/watch?v=ataGotQ7ir8 optional: Microsoft’s AI beats Ms. Pac-Man https://techcrunch.com/2017/06/15/microsofts-ai-beats-ms-pac-man/ intro to NN https://www.

  • https://unity.com/products/machine-learning-agents https://www.youtube.com/watch?v=m_LxmQOS20Y Game A.I. Classic A.I. FSM Random / Fuzzy Sensor systems Flocking A* pathfinding Navigation Mesh Behaviour Trees introduzione video: https://www.youtube.com/watch?v=uq8hnnkAxsw FPS video: https://www.youtube.com/watch?v=6VBCXvfNlCM introduzione: https://www.gamasutra.com/blogs/ChrisSimpson/20140717/221339/Behavior_trees_for_AI_How_they_work.php molte soluzioni: su asset store: https://assetstore.

  • GameTech AI introduzione AI Methods Representation Utility Finite State Machines Behavior Trees Utility-Based AI TreeSearch Evolutionary Computation hill climber Evolutionary Algorithms Supervised Learning Reinforcement Learning Unsupervised Learning Clustering Frequent Pattern Mining Hybrid Algorithms Neuroevolution Giocare Perché e Come Can AI PlayGames?

  • 26-2-2021 analisi 8 esercizi board games exercises ML-AGENTS generate