RL on Jaco Arm in DeepMind Control Suite

This repository implements TD3 and DDPG on DeepMind Control Suite tasks.

• This repository needs the jaco_arm branch of dm_control forked here.
• The agent implementations are taken from the Official TD3 repository.

Usage

You can train an agent for the reaching task on Jaco arm by running:

python main.py --domain jaco --task easy