-
Solving the tasks using a TensorFlow implementation of DDPG.
-
All the code can be found in this repository.
-
Do not forget to set the environment name (env_name) to 'InvertedPendulum-v1' or 'MountainCarContinuous-v0' in the file parameters.py.
-
The provided results were obtained by running a single worker. To replicate the results run the following commands in two different consoles:
python ddpg.py --job_name="ps" --task_index=0
python ddpg.py --job_name="worker" --task_index=0
Last active
September 6, 2017 14:56
-
-
Save camigord/48d193a61c624a20071465bcf3504565 to your computer and use it in GitHub Desktop.
Solving MountainCarContinuous using DDPG
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment