Yunho Choi, Kyungjae Lee, and Songhwai Oh, "Distributional Deep Reinforcement Learning with a Mixture of Gaussians," in Proc. of the IEEE International Conference on Robotics and Automation (ICRA), May 2019.
adapted from https://github.com/Silvicek/distributional-dqn
- install baseline https://github.com/ececyh/baselines (pip install -e .)
- pip install gym, box2d (if swig error, sudo apt-get install swig)
- import train_car_racing and run the exp function ex) train_car_racing.exp(buffer_size=1e6, action_res=[5,5,5])
Implementation of 'A Distributional Perspective on Reinforcement Learning' and 'Distributional Reinforcement Learning with Quantile Regression' based on OpenAi DQN baseline.
Install the OpenAi fork https://github.com/Silvicek/baselines (parent changes a lot, compatibility isn't guaranteed) Then install requirements
pip3 install -r requirements.txt
For simple benchmarking:
python3 train_[{cartpole, pong}].py
python3 enjoy_[{cartpole, pong}].py
For full Atari options see help
python3 train_atari.py --help
after learning, you can visualize the distributions by running
python3 enjoy_atari.py --visual ...
This implementation has been successfully tested on: Pong, Qbert, Seaquest
Some baseline features not supported (prioritized replay, double q-learning, dueling)