by Jim DiLorenzo | Released April 2019 | ISBN: 9781789950748

Write Reinforcement Learning agents in TensorFlow & TRFL, with easeAbout This VideoHands-on emphasis on code examples to get you experienced with TRFL quickly.Straightforward implementations of TRFL that let you utilize a trusted codebase in your projects. Save time implementing RL agents and algorithms, unit testing, and debugging code.Covers the TRFL library more comprehensively than any other course. Examples teach the easy integration and expansion of RL algorithms with TRFL building blocks.In DetailThe TRFL library is a collection of key algorithmic components that are used for a large number of DeepMind agents such as DQN, DDPG, and the Importance of Weighted Actor Learner Architecture. With this course, you will learn to implement classical RL algorithms as well as other cutting-edge techniques.This course will help you get up-to-speed with the TRFL library quickly, so you can start building your own RL agents. Without wasting much time on theory, the course dives straightaway into designing and implementing RL algorithms.By the end, you will be quite familiar with the tool and will be ready to put your knowledge into practice in your own projects. Show and hide more

1. Chapter 1 : Introduction and Classic Reinforcement Learning
   • The Course Overview 00:03:02
   • Set Up and Installation 00:02:16
   • Getting Started with TD Learning 00:04:27
   • Exploiting Off-policy Efficiency Using Q Learning 00:03:34
   • Comparing On-policy Methods with SARSA and SARSE 00:03:41
2. Chapter 2 : Deep Reinforcement Learning with Deep Q Networks and Enhancements
   • Implementing a Deep Q Network and Applying Target Network Updates 00:08:09
   • Modifying a DQN with Double DQN, Persistent DQN, and Huber Loss 00:04:11
   • Improving a DQN with Distributional Q Learning 00:05:13
3. Chapter 3 : Fundamentals of Deep RL: Policy Gradient Methods
   • Utilizing Policy Gradient Methods 00:06:49
   • Increasing Exploration with Policy Entropy Loss 00:05:22
   • Applying Actor-Critic with A3C and A2C 00:04:46
   • Performing Deterministic Policy Gradients 00:04:28
4. Chapter 4 : Essential RL: TD(λ) Learning
   • Deploying TD(λ) 00:04:17
   • Balancing Bias and Variance with Generalized λ Returns 00:03:00
   • Applying Q(λ) 00:02:28
   • Working with Multi-step Forward View 00:02:15
5. Chapter 5 : Cutting Edge RL with Impala and Unreal
   • Using Importance Sampling with Retrace (λ) 00:03:20
   • Getting Started with Impala with V-Trace 00:03:29
   • Augmenting an Agent with Unreal and Pixel Control 00:04:14
Show and hide more