This is the code repository for Reinforcement Learning with TensorFlow & TRFL [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
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.
- Design chatbots using cutting-edge NLP algorithms and the latest TensorFlow frameworks from the industry
- Build chatbots that are able to handle hundreds of customer queries at a time
- Develop generative chatbots which follow the flow of the conversation and respond appropriately
- Make your chatbots contextually aware and attentive, to provide solutions quickly and easily
- Gain customer insights and provide feedback to improve customer satisfaction
- Employ chatbots that help businesses reduce the staff required, thus saving money
- Automate repetitive tasks (through chatbots) that are otherwise prone to errors if done by humans
To fully benefit from the coverage included in this course, you will need:
To be an ML or DL Engineer who has been working with TensorFlow and would now like to learn how to design and implement robust Reinforcement Learning algorithms in TRFL.
Experience with Reinforcement Learning and TensorFlow is assumed.
This course has the following software requirements:
Recommended hardware requirements
For an optimal experience with the practical activities, we recommend access to a Cloud computing resource or the following configuration:
OS: Windows 7 or greater, MacOS, or Ubuntu 16.04 Processor: Intel i5 Series (or equivalent) or better Memory: 8 GB RAM Storage: At least 10 GB of storage (SSD preferred)
Software requirements
For offline usage:
Operating system: Windows, MacOS, or Linux Python 3.6 TRFL (pip install trfl) TensorFlow version 1.12 or greater (pip install tensorflow or pip install tensorflow-gpu TensorFlow probability (pip install tensorflow-probability) wrapt (pip install wrapt)