Simulation framework for learning an object-agnostic control policy for pick-and-place operation on a novel 6-DoF parallel manipulator (aka D3 arm) using Deep reinforcement learning, specifically DDPG (Deep Deterministic Policy Gradient) + HER (Hindshight Experience Replay) algorithm.
- Install MuJoCo
- Download the MuJoCo version 2.1 binaries for Linux.
- Extract the downloaded mujoco210 directory into ~/.mujoco/mujoco210.
- Clone this repository
cd ~
git clone -b main https://github.com/biorobotics/Wombat_robosuite.git
- Install the dependencies
cd Wombat_robosuite/robosuite
pip3 install -r requirements.txt
- Test your installation with
python demos/demo_random_action.py
cd ~/Wombat_robosuite/robosuite/HER+DDPG/hindsight-experience-replay-latest
python D3_train_dyn_rand.py
Weights will be stored in 'saved_models/PickPlaceiPhone'. Currently, the best trained weights are with the name 'Model_dyn_rand_epoch_50.pt'.
cd ~/Wombat_robosuite/robosuite/HER+DDPG/hindsight-experience-replay-latest
python D3_demo_dyn_rand.py
This project builds upon the excellent work done in the Robosuite Framework. Many thanks to all the contributors involved.