Cargando…
Learn Unity ML-Agents - Fundamentals of Unity Machine Learning : Incorporate New Powerful ML Algorithms Such As Deep Reinforcement Learning for Games.
Unity Machine Learning Agents allows researchers and developers to create games and simulations using the Unity Editor which serve as environments where intelligent agents can be trained with machine learning methods through a simple-to-use Python API. This book takes you from the basics of Reinforc...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Birmingham :
Packt Publishing Ltd,
2018.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Cover; Title Page; Copyright and Credits; Dedication; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Introducing Machine Learning and ML-Agents; Machine Learning; Training models; A Machine Learning example; ML uses in gaming; ML-Agents; Running a sample; Setting the agent Brain; Creating an environment; Renaming the scripts; Academy, Agent, and Brain; Setting up the Academy; Setting up the Agent; Setting up the Brain; Exercises; Summary; Chapter 2: The Bandit and Reinforcement Learning; Reinforcement Learning; Configuring the Agent; Contextual bandits and state.
- Building the contextual banditsCreating the ContextualDecision script; Updating the Agent; Exploration and exploitation; Making decisions with SimpleDecision; MDP and the Bellman equation; Q-Learning and connected agents; Looking at the Q-Learning ConnectedDecision script; Exercises; Summary; Chapter 3: Deep Reinforcement Learning with Python; Installing Python and tools; Installation; Mac/Linux installation; Windows installation; Docker installation; GPU installation; Testing the install; ML-Agents external brains; Running the environment; Neural network foundations; But what does it do?
- Deep Q-learningBuilding the deep network; Training the model; Exploring the tensor; Proximal policy optimization; Implementing PPO; Understanding training statistics with TensorBoard; Exercises; Summary; Chapter 4: Going Deeper with Deep Learning; Agent training problems; When training goes wrong; Fixing sparse rewards; Fixing the observation of state; Convolutional neural networks; Experience replay; Building on experience; Partial observability, memory, and recurrent networks; Partial observability; Memory and recurrent networks; Asynchronous actor
- critic training.
- Multiple asynchronous agent trainingExercises; Summary; Chapter 5: Playing the Game; Multi-agent environments; Adversarial self-play; Using internal brains; Using trained brains internally; Decisions and On-Demand Decision Making; The Bouncing Banana; Imitation learning; Setting up a cloning behavior trainer; Curriculum Learning; Exercises; Summary; Chapter 6: Terrarium Revisited
- A Multi-Agent Ecosystem; What was/is Terrarium?; Building the Agent ecosystem; Importing Unity assets; Building the environment; Basic Terrarium
- Plants and Herbivores; Herbivores to the rescue.
- Building the herbivoreTraining the herbivore; Carnivore: the hunter; Building the carnivore; Training the carnivore; Next steps; Exercises; Summary; Other Books You May Enjoy; Index.