TensorFlow Agents PyBullet Usage Example
This example shows how to install TensorFlow agents and use it on custom environments, such as the environments that come with PyBullet.
It works for both Python 3 and Python 2. Just replace pip3
and python3
with
pip2
and python2
.
Set up the dependencies:
sudo pip3 install -U tensorflow
sudo pip3 install -U gym
sudo pip3 install -U ruamel.yaml
Install TensorFlow agents from PyPi:
sudo pip3 install agents
Instead, if you want to hack the code, clone the repository:
git clone git@github.com:tensorflow/agents.git
cd agents
sudo python3 setup.py develop
Run the script to train an agent:
python3 agents_example.py --mode train --logdir ~/experiments/agents --config pybullet_ant
Launch TensorBoard to visualize training:
tensorboard --logdir=~/experiments/agents
During or after training, use this script to render videos:
python3 agents_example.py visualize ~/experiments/agents/ppo_on_pybullet_ant