Configuration

Let's first define a list of configuration parameters for the environment using a dictionary, shown as follows:

# Default environment configurationENV_CONFIG = {    "enable_planner": True,    "use_depth_camera": False,    "discrete_actions": True,    "server_map": "/Game/Maps/" + city,    "scenarios": [scenario_config["Lane_Keep_Town2"]],    "framestack": 2, # note: only [1, 2] currently supported    "early_terminate_on_collision": True,    "verbose": False,    "render_x_res": 800,    "render_y_res": 600,    "x_res": 80,    "y_res": 80}

scenario_config defines several parameters that are useful for creating a variety of driving scenarios. The scenario configuration is described in the scenarios.json file, which can be found in the book's code repository at ch7/carla-gym/carla_gym ...

Get Hands-On Intelligent Agents with OpenAI Gym now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.