July 2018
Intermediate to advanced
254 pages
8h 12m
English
Let's start training an agent in the CARLA driving environment! First, make sure your GitHub fork is up to date with the upstream master so that you have the latest code from the book's repository. Since the CARLA environment we created in the previous chapter is compatible with the OpenAI Gym interface, it is actually easy to use the CARLA environment for training, just like any other Gym environment. You can train the n-step advantage actor-critic agent using the following command:
(rl_gym_book) praveen@ubuntu:~/HOIAWOG/ch8$ python a2c_agent --env Carla-v0
This will launch the agent's training process, and like we saw before, a summary of the progress will be printed to ...
Read now
Unlock full access