Skip to content
Implementation of 'A Distributional Perspective on Reinforcement Learning' and 'Distributional Reinforcement Learning with Quantile Regression' based on OpenAi DQN baselines.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
distdeepq [0, 255] -> [0, 1] Nov 9, 2017
LICENSE
README.md quantile->readme Nov 19, 2017
dist-dqn.gif better gif Nov 7, 2017
enjoy_atari.py fix enjoy atari env Nov 7, 2017
enjoy_cartpole.py
enjoy_pong.py pong is enjoyable Nov 18, 2017
quantile-dqn.gif quantile->readme Nov 19, 2017
requirements.txt requirements.txt Oct 31, 2017
train_atari.py fixed wrappers - up to date with baselines Oct 31, 2017
train_cartpole.py visualization working in all settings Sep 20, 2017
train_pong.py pong training time increase Nov 8, 2017
wang2015_eval.py fixed json loading Sep 12, 2017

README.md

Distributional DQN

Implementation of 'A Distributional Perspective on Reinforcement Learning' and 'Distributional Reinforcement Learning with Quantile Regression' based on OpenAi DQN baseline.

C51:

c51

Quantile Regression: (see branch quantile)

quantile regression

Installation

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

Usage:

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)

You can’t perform that action at this time.