RL-implementations

The DDPG / TD3 implementations are originally from : this repository

Usage Examples

Learn a policy

Warning: This code is intended to be run from a higher level implementations.

To learn a policy with one of the algorithm , one must run :

python learn_policy.py --algorithm DDPG --environment 'MountainCarContinuous-v0'

For a comprehensive summary of all the parameters and their description please run :

python learn_policy.py --help

Run a policy

Warning: This code is intended to be run from a higher level implementations.

python run_policy.py --algorithm DDPG --environment 'MountainCarContinuous-v0'

Reminder

This reposity is still under active development and some functionalities might break.