the section "Read Data from Dataset" should be updated. This part is implemented through Scenarionet.
It is recommended to give the calculation process of vehicle dynamics simulation. Convenient for users to develop speed or trajectory control. Also for 'random_agent_model' in config.
DI-drive now give an exmaple about metadrive reinforcement learning. Can be added to the ecosystem.
Doc Sections:
xvfb
Installation:
RL Training with MetaDrive:
gym.make
/gym.register
in doc and code!Concepts and customization:
Engine:
Objects:
Render:
vglrun
might be required for Headless runningSensors:
GUI:
Others:
steering_range
viaagent_configs
.Debug:
Ecosystem:
Others
horizon
andmax_step_per_agent
still work.target_vehicle_config
will overwritevehicle_config
To clean: