coach
coach copied to clipboard
Imitation Learning API in CARLA Environment
I wonder if there's support for using Imitation Learning API in Carla's environment.
For Example, if I try imitation learning on an Atari Environment I use: coach -et rl_coach.environments.gym_environment:Atari -lvl BreakoutDeterministic-v4 --play
When I try the same argument in Carla, for example: coach -et rl_coach.environments.carla_environment:CarlaEnvironment --play
The init in CarlaEnvironment needs some attributes unlike Atari one.
In case there was support for this, how can I make it work?
BTW, thanks for the great work.