How can we collect image and action ([steering_angle,acceleration] data using the Arrival simulator? As the documentation below says we can collect our own data.
@jon_francis to share details
There are a couple options here:
- Save an agent’s transitions, automatically: agents/sac_agent.py · master · Learn to Race / l2r-starter-kit · GitLab
- Save queue: L82-93
record_experienceconfiguration flag: L328-342, L357-359, L479-494
- Record transitions from the simulator, manually; see the following thread for some hints: