English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 19m | 347 MB
Leverage TRFL to create and implement RL models with ease
The 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.
In each section of the course, we walk through part of the TRFL library. We explain how TRFL is used with clear code examples that highlight integrating TRFL into TensorFlow code, making it easy to deploy TRFL in new or existing projects. While this course emphasizes practical TRFL usage, we provide explanations that relate the TRFL library to the underlying theory and provide further resources for those wanting to know more.
What You Will Learn
- Build projects with TRFL and TensorFlow and integrate essential RL building blocks into existing code
- Save time spent implementing, testing, and debugging by increasing code reliability
- Relate TRFL methods to the leading RL algorithms and theory
- Discover improvements to RL algorithms such as DQN and DDPG with TRFL blocks—for example, advanced
- target network updating, Double Q Learning, and Distributional Q Learning
- Use cutting-edge techniques behind IMPALA and UNREAL such as V-Trace and Pixel Control
- Modify RL agents to include multistep reward techniques such as TD lambda
- Explore policy gradient techniques used in leading algorithms with TRFL methods for discrete and continuous action spaces
- Create TRFL-based RL agents with classic RL methods such as TD Learning, Q Learning, and SARSA