Conventions used

There are a number of text conventions used throughout this book.

Code in text: Indicates code words used in the recipes. Here is an example: "We will start with the implementation of the save method in the Actor class to export the Actor model to TensorFlow's SavedModel format."

A block of code is set as follows:

def save(self, model_dir: str, version: int = 1):
    actor_model_save_dir = os.path.join(model_dir, "actor", str(version), "model.savedmodel")
    self.model.save(actor_model_save_dir, save_format="tf")
    print(f"Actor model saved at:{actor_model_save_dir}") 

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

if args.agent != "SAC":
    print(f"Unsupported Agent: {args.agent}. Using SAC Agent")
    args.agent = "SAC"
    # Create an instance of the Soft Actor-Critic Agent
    agent = SAC(env.observation_space.shape, env.action_space) 

Any command-line input or output is written as follows:

(tfrl-cookbook)praveen@desktop:~/tensorflow2-reinforcement-learning-cookbook/src/ch7-cloud-deploy-deep-rl-agents$ python 3_training_rl_agents_using_remote_sims.py 

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "Click on the Open an Existing Project option and you will see a popup asking you to choose the directory on your filesystem. Navigate to the Chapter 9 recipes and choose 9.2_rl_android_app."

Tips or important notes

Appear like this.